io.github.getgapup/mcp-knowledge

Est-ce que io.github.getgapup/mcp-knowledge est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.getgapup/mcp-knowledge » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 279 outils

• abm_architect≈ 532 tokens

  Architecte ABM — Gapup agent-payable C-suite expertise (CMO). Returns a structured, audited deliverable. Reference case: Gapup Hub — ABM 20 comptes nommés · Budget €120k · Tier 1×5 + Tier 2×15 · Playbooks 3 niveaux. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (8)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • company · object · requis
  • product · object · requis
  • salesTeam · object · optionnel
  • icpCriteria · array · requis
  • abmBudgetEur · number · optionnel
  • targetAccounts · array · requis
  • currentChannels · array · optionnel

  Exemple d'appel

  {"name": "abm_architect", "arguments": {"company": {}, "product": {}, "icpCriteria": [], "targetAccounts": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• abm_lookalike_account_finder≈ 710 tokens

  As a CMO, discover 50 B2B accounts that closely match your top 10 customers' tech stacks and firmographics. This tool analyzes public web data including robots.txt and OpenGraph metadata to identify lookalike accounts for targeted ABM campaigns. Input your top customer domains and desired firmographic filters to receive a ranked list of potential targets with matching technologies and company attributes.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • tech_stack_keywords · array · optionnel
    Specific technologies to match in lookalike accounts
  • firmographic_filters · object · optionnel
  • top_customer_domains · array · requis
    List of top 10 customer domains to use as seed accounts

  Exemple d'appel

  {"name": "abm_lookalike_account_finder", "arguments": {"top_customer_domains": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"stats": {}, "status": "final", "sources": [], "warnings": [], "lookalike_accounts": [], "matched_technologies": []}}

• account_expansion_mapper≈ 585 tokens

  Mapping d'expansion comptes — Gapup agent-payable C-suite expertise (CRO). Returns a structured, audited deliverable. Reference case: Notion B2B Enterprise — top 30 strategic accounts · expansion plays NRR 130%+ target · Snowflake/Shopify/Vercel/Stripe analyzed. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • company · object · requis
  • accounts · array · requis
  • ownership · object · requis

  Exemple d'appel

  {"name": "account_expansion_mapper", "arguments": {"company": {}, "accounts": [], "ownership": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• action_plan_esg≈ 608 tokens

  Plan d'action ESG — Gapup agent-payable C-suite expertise (SUSTAINABILITY). Returns a structured, audited deliverable. Reference case: TechCorp SAS — Plan ESG 36 mois (500 FTE, €60M CA, score 54→76/100). Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (8)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • company · object · requis
  • horizon · string · requis · 12 mois | 24 mois | 36 mois
  • ambitions · object · requis
  • targetLabels · array · optionnel
  • currentScores · object · optionnel
  • availableResources · object · requis

  Exemple d'appel

  {"name": "action_plan_esg", "arguments": {"company": {}, "horizon": "12 mois", "ambitions": {}, "availableResources": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• adversarial_input_stress_tester≈ 541 tokens

  An asynchronous risk assessment tool that evaluates AI model resilience against adversarial inputs following NIST AI Risk Management Framework (RMF) red-teaming protocols. Designed for security and compliance personas, it accepts model outputs or decision boundaries and returns structured risk scores, failure modes, and adversarial examples. Requires async:true to avoid timeout errors. Outputs include status, warnings, and source references.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • maxTests · integer · optionnel
    Maximum number of adversarial tests to run
  • modelOutput · string · requis
    The AI model's output or decision to be stress-tested
  • adversarialDataset · array · optionnel
    Optional custom adversarial inputs to test
  • sensitivityThreshold · number · optionnel
    Threshold for flagging high-risk adversarial examples

  Exemple d'appel

  {"name": "adversarial_input_stress_tester", "arguments": {"modelOutput": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "riskScore": 1, "failureModes": [], "adversarialExamples": []}}

• affiliate_fraud_clickstream_detector≈ 636 tokens

  Analyzes affiliate clickstream data from Common Crawl to flag potential fraud patterns (duplicate IPs, rapid clicks, device spoofing). Designed for CMOs to validate affiliate traffic quality and prevent budget waste. Inputs: affiliate network name and date range. Outputs: fraud probability score, suspicious IP list, and pattern analysis. Keywords: affiliate fraud detection, clickstream analysis, marketing attribution, traffic validation.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • threshold · number · optionnel
    Fraud probability threshold (0.1-0.99)
  • date_range · object · requis
  • affiliate_network · string · requis
    Name of the affiliate network to analyze (e.g., 'CJ Affiliate', 'Rakuten')

  Exemple d'appel

  {"name": "affiliate_fraud_clickstream_detector", "arguments": {"date_range": {}, "affiliate_network": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "suspicious_ips": [], "fraud_probability": 1, "patterns_detected": [], "total_clicks_analyzed": 1}}

• africa_trade_barrier_breaker≈ 634 tokens

  As a COO, analyze non-tariff trade barriers (NTBs) across African trade corridors using WITS and UNCTAD STAT data. Input origin/destination countries and product HS codes to receive barrier mapping with severity scores and actionable mitigation strategies. Returns structured risk assessment, regulatory compliance gaps, and supply chain optimization recommendations. Pass async:true to avoid timeout.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • hs_code · string · optionnel
    6-digit Harmonized System product code
  • origin_country · string · requis
    ISO 3-letter country code for export origin
  • destination_country · string · requis
    ISO 3-letter country code for import destination
  • include_regulatory_details · boolean · optionnel
    Whether to include detailed regulatory text in output

  Exemple d'appel

  {"name": "africa_trade_barrier_breaker", "arguments": {"origin_country": "texte", "destination_country": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "barrier_summary": {}, "trade_flow_impact": {}, "regulatory_details": [], "mitigation_strategies": []}}

• africa_trade_finance_esg_rater≈ 550 tokens

  As a COO, evaluate ESG compliance of African trade finance providers using World Bank WITS trade statistics and CDP climate disclosure data. Input the financial institution's name or identifier, and receive an ESG rating with breakdown across environmental, social, and governance dimensions. Ideal for due diligence on trade partners or portfolio risk assessment. Pass async:true to avoid timeout.

  Paramètres, retour & exemple (4)

  Paramètres

  • year · number · optionnel
    Assessment year (2018-2023)
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • countryCode · string · optionnel
    ISO 2-letter country code (e.g., 'ZA' for South Africa)
  • institutionName · string · requis
    Full name of the trade finance provider (e.g., 'Standard Bank Group')

  Exemple d'appel

  {"name": "africa_trade_finance_esg_rater", "arguments": {"institutionName": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "esgRating": "A", "socialScore": 1, "tradeVolume": 1, "carbonIntensity": 1, "governanceScore": 1, "environmentalScore": 1}}

• africa_trade_preference_arbitrage≈ 639 tokens

  Analyzes AGOA (African Growth and Opportunity Act) and EBA (Everything But Arms) trade preference arbitrage opportunities for COOs evaluating export strategies. Compares tariff rates, trade volumes, and preference utilization across eligible African countries using WITS and OECD trade data. Returns structured analysis of potential duty savings, market access advantages, and compliance requirements. — pass async:true REQUIRED to avoid x402 timeout.

  Paramètres, retour & exemple (6)

  Paramètres

  • year · integer · optionnel
    Reference year for trade data
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • hs_code · string · requis
    6-10 digit Harmonized System product code
  • exporting_country · string · requis
    ISO 2-letter country code of African exporter
  • importing_country · string · optionnel
    ISO 2-letter country code of target market (US/EU)
  • preference_scheme · string · optionnel · AGOA | EBA
    Trade preference scheme to analyze

  Exemple d'appel

  {"name": "africa_trade_preference_arbitrage", "arguments": {"hs_code": "texte", "exporting_country": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "duty_savings_pct": 1, "trade_volume_usd": 1, "market_access_score": 1, "compliance_requirements": [], "preference_utilization_rate": 1}}

• africa_trade_preference_optimizer≈ 790 tokens

  As a COO, analyze AGOA/EBA duty savings opportunities with HS code-level trade route optimization. Input origin country, destination country, and HS code to receive duty savings estimates, optimal trade routes, and preference utilization recommendations. Uses UN Comtrade trade flow data, WCO tariff schedules, and African Union trade agreement rules. Ideal for export market evaluation, supply chain optimization, and trade agreement compliance analysis. Keywords: AGOA, EBA, duty savings, trade optimization, HS code, African trade, export strategy.

  Paramètres, retour & exemple (6)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • hsCode · string · requis
    6-10 digit Harmonized System code (e.g., '010121' for live horses)
  • quantity · number · optionnel
    Estimated annual export quantity in units
  • valueUsd · number · optionnel
    Estimated annual export value in USD
  • originCountry · string · requis
    ISO 3166-1 alpha-3 country code of export origin (e.g., 'KEN' for Kenya)
  • destinationCountry · string · requis
    ISO 3166-1 alpha-3 country code of import destination (e.g., 'USA' for United States)

  Exemple d'appel

  {"name": "africa_trade_preference_optimizer", "arguments": {"hsCode": "texte", "originCountry": "texte", "destinationCountry": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "dutySavings": 1, "optimalRoute": {}, "alternativeRoutes": [], "complianceWarnings": []}}

• agoa_eba_intelligence≈ 491 tokens

  Intelligence préférentielle AGOA (US→Africa) et EBA/GSP (EU→Africa). Vérifie l'éligibilité d'un pays africain aux programmes tarifaires préférentiels, l'éligibilité d'un produit par code HS, identifie les meilleures opportunités d'export Afrique→US/EU, et fournit les règles de conformité (rules of origin, valeur ajoutée, docs). Différenciateur Africa diaspora : 39 pays AGOA + 47 LDCs EBA encodés. Sources : AGOA.info · EU EBA · EU GSP+ · WTO Tariff · UN Comtrade.

  Paramètres, retour & exemple (5)

  Paramètres

  • mode · string · requis · country_eligibility | product_eligibility | trade_opportunity | compliance_check
    Mode d'analyse : 'country_eligibility' (statut AGOA/EBA/GSP d'un pays africain) | 'product_eligibility' (éligibilité d'un produit par code HS) | 'trade_opportunity' (top opportunités export Afrique→US/EU) | 'compliance_check' (rules of origin, seuils valeur ajoutée, documentation)
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • hs_code · string · optionnel
    Code HS (Harmonized System) 6+ chiffres (requis pour product_eligibility). Exemple : '620342' = pantalons coton homme, '090111' = café arabica non torréfié, '060310' = fleurs fraîches.
  • country_iso · string · optionnel
    Code ISO 2-lettres du pays africain (requis pour country_eligibility). Exemples : KE=Kenya, NG=Nigeria, ZA=Afrique du Sud, ET=Éthiopie, LS=Lesotho, GH=Ghana.
  • destination · string · optionnel · US | EU | both
    Marché de destination pour trade_opportunity : 'US', 'EU', ou 'both' (défaut). Ignoré pour les autres modes.

  Exemple d'appel

  {"name": "agoa_eba_intelligence", "arguments": {"mode": "country_eligibility"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ai_act_incident_response≈ 578 tokens

  Generates EU AI Act incident response playbooks with regulator notification templates for risk management teams. Inputs include incident severity, AI system type, and affected stakeholders. Outputs structured playbook steps, regulator notification drafts, and compliance checklists. Essential for high-risk AI system breaches requiring formal EU notification — pass async:true REQUIRED to avoid x402 timeout. Keywords: AI Act compliance, incident response, regulator notification, risk management, ISO 27035, NIST SP 800-61.

  Paramètres, retour & exemple (6)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • severity · string · requis · low | medium | high | critical
  • incident_type · string · requis · bias | safety_failure | data_breach | model_failure | other
  • ai_system_type · string · optionnel · high_risk | limited_risk | minimal_risk
  • incident_description · string · optionnel
  • affected_stakeholders · array · optionnel

  Exemple d'appel

  {"name": "ai_act_incident_response", "arguments": {"severity": "low", "incident_type": "bias"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "next_steps": [], "playbook_steps": [], "compliance_checklist": [], "regulator_notification": {}}}

• ai_act_sandbox_regulatory_sandbox≈ 635 tokens

  A legal-focused tool for simulating EU AI Act regulatory sandbox submissions. Provides structured feedback on compliance, risk levels, and required documentation based on EUR-Lex and OECD AI Policy Observatory sources. Accepts AI system descriptions, intended use cases, and technical specifications as input. Returns detailed assessment with warnings, citations, and actionable recommendations for legal teams and AI developers.

  Paramètres, retour & exemple (6)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • sector · string · optionnel · healthcare | finance | transport | education | public | other
    Primary sector of application
  • riskLevel · string · requis · minimal | limited | high | unacceptable
    Self-assessed risk level of the AI system
  • intendedUse · string · requis
    Primary and secondary use cases of the AI system
  • documentation · array · optionnel
    List of provided documentation types (e.g., 'technical', 'ethical', 'data')
  • systemDescription · string · requis
    Detailed description of the AI system including purpose, architecture, and data sources

  Exemple d'appel

  {"name": "ai_act_sandbox_regulatory_sandbox", "arguments": {"riskLevel": "minimal", "intendedUse": "texte", "systemDescription": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "assessment": {}}}

• ai_act_training_data_audit≈ 516 tokens

  As a CTO, audit AI training datasets for EU AI Act compliance with bias detection and regulatory risk assessment. Inputs: dataset identifier (Hugging Face ID or URL) and optional risk thresholds. Outputs: compliance score, bias metrics, regulatory warnings, and source references. Ideal for pre-deployment risk evaluation. Pass async:true to avoid timeout.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • dataset_id · string · requis
    Hugging Face dataset identifier or direct URL to dataset
  • risk_threshold · number · optionnel
  • include_bias_metrics · boolean · optionnel

  Exemple d'appel

  {"name": "ai_act_training_data_audit", "arguments": {"dataset_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "bias_metrics": {}, "compliance_score": 1, "dataset_metadata": {}, "regulatory_warnings": []}}

• ai_governance_full_report_async≈ 731 tokens

  Audit EU AI Act complet (Règlement UE 2024/1689) — implémentation native audit-grade. Classifie le système IA selon les 4 tiers de risque (unacceptable/high_risk/limited_risk/minimal_risk/gpai) sur la base de l'Annexe III et de l'Article 5. Produit : (1) classification tier + justification + articles applicables, (2) checklist conformité Articles 9-15 + 50 + 53-55, (3) gaps documentation Annexe IV, (4) mapping ISO 42001, (5) deadlines EU AI Act 2025-2029, (6) estimation coût et effort, (7) top 10 recommandations P0/P1/P2. Retourne immédiatement (<300ms) un job_id. Poller avec ai_governance_full_report_result(job_id) après eta_seconds (~90s). Cache 7 jours pour inputs identiques. Async tool — register a webhook via `webhooks_manage(register, url, [job.completed])` to receive callbacks instead of polling. Faster + lighter. DISCLAIMER : non substitutif à un avis juridique professionnel.

  Paramètres, retour & exemple (7)

  Paramètres

  • company_size · string · optionnel · startup | smb | mid | large | enterprise
    Taille entreprise : startup (≤50), smb (51-250), mid (251-1000), large (1001-5000), enterprise (>5000)
  • data_sources · array · optionnel
    Sources de données utilisées par le système IA
  • affected_persons · array · optionnel
    Catégories de personnes affectées par les décisions du système (ex: candidats, employés, clients)
  • geographic_scope · array · optionnel
    Zones géographiques de déploiement (ex: 'EU', 'France', 'Global')
  • intended_purpose · string · requis
    Finalité prévue du système IA : à quoi sert-il concrètement
  • deployment_context · string · optionnel · internal | public | b2b | b2c
    Contexte de déploiement : interne (usage employés), public, B2B, B2C
  • ai_system_description · string · requis
    Description détaillée du système IA : ce qu'il fait, comment il fonctionne, quelles décisions il prend

  Exemple d'appel

  {"name": "ai_governance_full_report_async", "arguments": {"intended_purpose": "texte", "ai_system_description": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"job_id": "texte", "status": "queued", "eta_seconds": 1, "submitted_at": "texte"}}

• ai_governance_full_report_result≈ 1258 tokens

  Poll the result of an ai_governance_full_report_async job. Returns status=pending while running, status=completed with the full EU AI Act governance audit report once done (risk_tier, compliance checklist Articles 9-15/50/53-55, Annex IV documentation gaps, ISO 42001 alignment, deadlines 2025-2029, cost estimate, top-10 recommendations P0/P1/P2, compliance_score), status=failed on error, or status=not_found if the job_id is unknown or expired (TTL 24h). Call this after the eta_seconds hint returned by ai_governance_full_report_async (~90s).

  Paramètres, retour & exemple (1)

  Paramètres

  • job_id · string · requis
    The job_id returned by ai_governance_full_report_async (prefix: aigfr_)

  Exemple d'appel

  {"name": "ai_governance_full_report_result", "arguments": {"job_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ai_governance_pilot≈ 502 tokens

  Pilotage de gouvernance IA — Gapup agent-payable C-suite expertise (RISK). Returns a structured, audited deliverable. Reference case: TalentScope SAS — scoring IA candidats RH (EU AI Act Annex III §4, high-risk). Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • company · object · requis
  • aiUseCases · array · requis
  • targetFrameworks · array · requis

  Exemple d'appel

  {"name": "ai_governance_pilot", "arguments": {"company": {}, "aiUseCases": [], "targetFrameworks": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• anti_demissions_hr≈ 527 tokens

  Bouclier anti-démissions — Gapup agent-payable C-suite expertise (COO). Returns a structured, audited deliverable. Reference case: Buffer Inc — détection des at-risk parmi 80 FTEs (Q1 2026). Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • company · object · requis
  • signals · object · requis
  • employees · array · requis

  Exemple d'appel

  {"name": "anti_demissions_hr", "arguments": {"company": {}, "signals": {}, "employees": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• arbitration_awards_lookup≈ 1026 tokens

  Commercial arbitration intelligence for litigation lawyers, M&A due diligence teams, sovereign wealth funds and trade finance compliance. Covers 8 major institutions: ICC, AAA, LCIA, HKIAC, SIAC, CIETAC, DIAC, ICDR. Three modes: • party_lookup — find awards by party name (searches 20 landmark public awards + JusMundi best-effort) • institution_index — browse awards and caseload stats per institution with date range filter • clause_check — audit an arbitration clause for missing elements (institution, seat, language, arbitrator count, governing law, binding nature) Note: Most arbitration awards are confidential. This tool surfaces public awards (Yukos, Crystallex, Achmea, etc.) plus redacted statistics from institutional annual reports. Private awards are not accessible. Cache: 24h (arbitration data is very stable). No API key required.

  Paramètres, retour & exemple (6)

  Paramètres

  • mode · string · requis · party_lookup | institution_index | clause_check
    party_lookup: search by party name or keyword. institution_index: browse awards by institution + stats. clause_check: audit an arbitration clause for issues.
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • query · string · requis
    For party_lookup: party name or keyword (e.g. "Yukos", "Russia"). For institution_index: institution name or keyword. For clause_check: full text of the arbitration clause to audit.
  • date_to · string · optionnel
    ISO date filter to (YYYY-MM-DD). Applied to award_date.
  • date_from · string · optionnel
    ISO date filter from (YYYY-MM-DD). Applied to award_date.
  • institution · string · optionnel · ICC | AAA | LCIA | HKIAC | SIAC | CIETAC | DIAC | ICDR
    Filter by institution. Default 'all'.

  Exemple d'appel

  {"name": "arbitration_awards_lookup", "arguments": {"mode": "party_lookup", "query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"mode": "texte", "query": "texte", "awards": [], "status": "partial", "sources": [], "clause_check": {}, "quality_score": 1, "institution_stats": {}}}

• attack_surface_monitor≈ 430 tokens

  Surveillance surface d'attaque — Gapup agent-payable C-suite expertise (RISK). Returns a structured, audited deliverable. Answers: Which Internet-facing assets of <domain> combine a critical CVE, an exposed service, and no WAF — top findings to fix in 14 days? · What is the attack surface of <domain>: subdomains, open ports, SSL/TLS grades, and associated CVEs? · Give me a CISO-ready ASM report with blast radius estimate and SLA-driven remediation plan for <domain>. · What is the email phishing risk for <domain>? Assess SPF/DMARC posture and recommend improvements. · During M&A due diligence, what are the top cyber exposures on <domain>'s Internet-facing infrastructure? Reference case: Velora Payments — 8 assets exposés · 2 critiques (CVE-2023-44487 HTTP/2 RapidReset, Admin panel ouvert) · . Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (6)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • domain · string · requis
  • exclusions · array · optionnel
  • scope_cidrs · array · optionnel
  • include_email_surface · boolean · requis

  Exemple d'appel

  {"name": "attack_surface_monitor", "arguments": {"domain": "texte", "include_email_surface": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• audit_pre_flight≈ 490 tokens

  Pré-audit comptable — Gapup agent-payable C-suite expertise (CFO). Returns a structured, audited deliverable. Reference case: Spendesk — Pré-audit commissaire · Readiness 74/100 · 4 findings critiques · Checklist 18 docs. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (6)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • audit · object · requis
  • company · object · requis
  • systems · array · requis
  • financials · object · requis
  • knownIssues · array · requis

  Exemple d'appel

  {"name": "audit_pre_flight", "arguments": {"audit": {}, "company": {}, "systems": [], "financials": {}, "knownIssues": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• banking_fee_negotiator≈ 676 tokens

  As a CFO-focused tool, banking_fee_negotiator analyzes your bank's fee structures (account maintenance, wire transfers, credit lines) and provides data-driven negotiation recommendations. Input your current fees and bank details to receive benchmark comparisons from World Bank and ECB SDW, along with specific levers to reduce costs. Ideal for optimizing treasury operations and improving financial efficiency. Keywords: bank fees, cost optimization, treasury management, financial benchmarking, negotiation strategy.

  Paramètres, retour & exemple (7)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • industry · string · optionnel
    Industry classification (e.g., 'manufacturing', 'retail')
  • bank_country · string · requis
    ISO 2-letter country code of the bank
  • credit_line_fee · number · optionnel
    Current annual credit line fee percentage
  • wire_transfer_fee · number · optionnel
    Current domestic wire transfer fee in USD
  • international_wire_fee · number · optionnel
    Current international wire transfer fee in USD
  • account_maintenance_fee · number · requis
    Current monthly account maintenance fee in USD

  Exemple d'appel

  {"name": "banking_fee_negotiator", "arguments": {"bank_country": "texte", "account_maintenance_fee": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "negotiation_levers": [], "credit_line_benchmark": 1, "wire_transfer_benchmark": 1, "international_wire_benchmark": 1, "account_maintenance_benchmark": 1}}

• battle_cards_live≈ 349 tokens

  Fiche de combat live — Gapup agent-payable C-suite expertise (CRO). Returns a structured, audited deliverable. Reference case: Gapup Hub vs McKinsey Lilli — Deal SaaS B2B €500k · Win rate +11 pts · 6 objections clés armées. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • ourOffer · string · requis
  • competitor · object · requis
  • dealContext · object · requis
  • knownWeaknesses · string · optionnel

  Exemple d'appel

  {"name": "battle_cards_live", "arguments": {"ourOffer": "texte", "competitor": {}, "dealContext": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• battle_plan≈ 397 tokens

  Plan de bataille marketing — Gapup agent-payable C-suite expertise (CMO). Returns a structured, audited deliverable. Reference case: Gapup Hub — Q3 2026 · Budget €120k · Pipeline €800k · 5 chantiers prioritaires. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (11)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • quarter · string · requis
  • teamSize · number · requis
  • arrTarget · number · requis
  • budgetEur · number · requis
  • arrCurrent · number · requis
  • companyName · string · requis
  • topChannels · array · requis
  • icpDescription · string · requis
  • currentBlockers · array · requis
  • primaryObjective · string · requis · pipeline | brand-awareness | product-launch | expansion | retention

  Exemple d'appel

  {"name": "battle_plan", "arguments": {"quarter": "texte", "teamSize": 1, "arrTarget": 1, "budgetEur": 1, "arrCurrent": 1, "companyName": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• bias_amplification_tracker≈ 469 tokens

  Tracks bias amplification in LLM outputs by analyzing fairness metrics from HuggingFace's model leaderboard. Designed for risk assessment personas to detect and quantify demographic, gender, or racial bias amplification in generated text. Accepts model identifiers or output samples, returns structured bias metrics and amplification trends.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • modelId · string · optionnel
    HuggingFace model identifier (e.g., 'facebook/opt-1.3b')
  • outputSamples · array · optionnel
    Array of LLM output strings to analyze for bias amplification
  • demographicGroups · array · optionnel
    Specific demographic groups to monitor (e.g., ['gender', 'race'])

  Exemple d'appel

  {"name": "bias_amplification_tracker", "arguments": {"async": true, "modelId": "texte", "outputSamples": [], "demographicGroups": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "biasMetrics": {}}}

• bond_covenant_esg_compliance_checker≈ 613 tokens

  As a CFO, quickly assess whether your bond covenants meet ESG compliance standards set by BIS and ECB. This tool analyzes covenant text against regulatory benchmarks, identifying potential ESG-related risks in carbon emissions, governance practices, and social impact clauses. Input bond covenant details and receive structured compliance insights with source references. Ideal for pre-issuance due diligence or ongoing monitoring of existing bond portfolios.

  Paramètres, retour & exemple (6)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • couponType · string · optionnel · fixed | floating | zero-coupon
    Type of bond coupon
  • covenantText · string · requis
    Full text of the bond covenant to analyze
  • issuerSector · string · optionnel
    Industry sector of the bond issuer (e.g., energy, finance)
  • jurisdiction · string · optionnel
    Legal jurisdiction governing the bond (e.g., EU, US)
  • maturityDate · string · optionnel
    Maturity date of the bond

  Exemple d'appel

  {"name": "bond_covenant_esg_compliance_checker", "arguments": {"covenantText": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "riskAreas": [], "complianceScore": 1, "recommendations": []}}

• bond_covenant_monitor≈ 546 tokens

  As a CFO, monitor bond covenant compliance by analyzing leverage ratios (debt-to-equity, debt-to-EBITDA) and interest coverage ratios using real-time financial data. Input a company's ticker symbol and optional covenant thresholds to receive compliance status, key financial metrics, and SEC filing references. Ideal for proactive debt management and regulatory compliance tracking. Keywords: bond covenants, leverage ratio, interest coverage, debt compliance, SEC filings, financial health.

  Paramètres, retour & exemple (3)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • ticker · string · requis
    Company ticker symbol (e.g., 'AAPL')
  • covenantThresholds · object · optionnel

  Exemple d'appel

  {"name": "bond_covenant_monitor", "arguments": {"ticker": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "debtToEquity": 1, "leverageRatio": 1, "lastFilingDate": "texte", "complianceStatus": "compliant", "interestCoverage": 1, "nextFilingDeadline": "texte"}}

• bp_narratif≈ 410 tokens

  Business Plan narratif — Gapup agent-payable C-suite expertise (CFO). Returns a structured, audited deliverable. Reference case: Stripe Series A 2012. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • raise · object · requis
  • company · object · requis
  • keyMetrics · array · requis

  Exemple d'appel

  {"name": "bp_narratif", "arguments": {"raise": {}, "company": {}, "keyMetrics": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• brand_builder≈ 544 tokens

  Architecte de marque — Gapup agent-payable C-suite expertise (CMO). Returns a structured, audited deliverable. Reference case: Pennylane — brand identity SaaS fintech B2B FR/EU (2023). Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • brand · object · requis
  • target · object · requis
  • founder · object · requis
  • existingAssets · object · optionnel

  Exemple d'appel

  {"name": "brand_builder", "arguments": {"brand": {}, "target": {}, "founder": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• brand_equity_voice_share_calculator≈ 574 tokens

  Calculates brand equity voice share for CMOs by analyzing mentions across 500K+ news articles and forums from Common Crawl and Wayback Machine. Inputs include brand name, competitors, and time range. Outputs voice share percentage, sentiment distribution, and top sources. Ideal for competitive benchmarking and brand visibility tracking. Pass async:true to avoid timeout.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • brand · string · requis
  • time_range · object · requis
  • competitors · array · optionnel
  • include_forums · boolean · optionnel

  Exemple d'appel

  {"name": "brand_equity_voice_share_calculator", "arguments": {"brand": "texte", "time_range": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "top_sources": [], "total_mentions": 1, "brand_voice_share": 1, "sentiment_distribution": {}, "competitor_voice_shares": []}}

• budget_variance_ai≈ 558 tokens

  Analyse d'écart budgétaire — Gapup agent-payable C-suite expertise (CFO). Returns a structured, audited deliverable. Answers: Explain the key drivers of the budget vs actual variance for <company> in <period> — what are the top 10 narrative explanations? · Which cost categories drove the budget overrun for <company> in <quarter>, and what corrective actions should management take? · Revise the Q4 forecast based on observed Q3 variances for <company> — give me 3 scenarios (base, optimistic, conservative). · Prepare a board-ready budget variance memo for <company> — <period>, budget €<X>M vs actual €<Y>M, with management actions. · What are the quick wins to reduce budget overspend for <company> by end of quarter without impacting growth targets? Reference case: Doctolib Q3 2026 — budget €38.5M vs actual €41.2M (+7.0%) — cloud + headcount + deals timing. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • entity · object · requis
  • budgetContext · object · requis

  Exemple d'appel

  {"name": "budget_variance_ai", "arguments": {"entity": {}, "budgetContext": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• building_enrich≈ 336 tokens

  Enrich a location with European building intelligence: roof surfaces (m²), parking areas, solar-obligation status under French loi APER and loi Climat-Résilience, existing solar installations. Covers 628,000 scanned roofs and 91,800 parkings across 6 EU countries (FR, DE, IT, ES, BE, NL). Deterministic database lookup — no LLM, no generation, sub-second.

  Paramètres, retour & exemple (5)

  Paramètres

  • lat · number · requis
    Latitude (WGS84)
  • lng · number · requis
    Longitude (WGS84)
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • radiusM · integer · optionnel
    Search radius in metres (default 150, max 500)
  • minAreaM2 · integer · optionnel
    Only return roofs/parkings at least this large, in m²

  Exemple d'appel

  {"name": "building_enrich", "arguments": {"lat": 1, "lng": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"query": {}, "roofs": [], "summary": {}, "parkings": [], "solarInstalled": []}}

• candidate_screening_ranking≈ 1264 tokens

  AI-powered candidate screening and ranking for recruiters, hiring managers, ATS providers and recruitment AI agents. Ingests a job description and 1-50 candidate resumes, returning a ranked shortlist with score breakdowns across five weighted criteria: skills_match (tech stack and soft skills extracted from JD vs resume), experience_match (years vs seniority level inferred from JD), education_match (degree level + top-school detection), role_progression (Junior to Senior to Lead patterns), culture_fit_estimate (remote/hybrid, startup vs enterprise). Per candidate: overall_score 0-100, matched/missing skills, red_flags (job hopping, employment gaps, seniority mismatch), green_flags (long tenure, promotions), 3-5 interview questions, fit_summary. Diversity signals are first-name proxies ONLY with mandatory ethical WARNING. All processing is local -- no external API calls, instant response, privacy-preserving.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • candidates · array · requis
    Array of candidate objects. Maximum 50.
  • role_country · string · optionnel
    Optional ISO 2-letter country code for regional context (informational).
  • job_description · string · requis
    Full text or summary of the job description and role requirements.
  • criteria_weights · object · optionnel
    Optional weighting per criterion. Default: skills=0.4, experience=0.2, education=0.1, progression=0.15, culture=0.15.

  Exemple d'appel

  {"name": "candidate_screening_ranking", "arguments": {"candidates": [], "job_description": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "partial", "sources": [], "nice_to_have": [], "quality_score": 1, "required_skills": [], "candidates_ranked": [], "diversity_signals": {}, "shortlist_recommended": [], "job_description_summary": "texte"}}

• cap_table_strategist≈ 596 tokens

  Stratège du cap table — Gapup agent-payable C-suite expertise (FUNDRAISING). Returns a structured, audited deliverable. Reference case: Aleph AI Series B — modèle dilution multi-rounds + simulations secondaires + hygiène equity · 5 scenarios. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (6)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • company · object · requis
  • plannedRounds · array · requis
  • currentCapTable · object · requis
  • founderObjectives · string · requis

  Exemple d'appel

  {"name": "cap_table_strategist", "arguments": {"company": {}, "plannedRounds": [], "currentCapTable": {}, "founderObjectives": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• capacity_planning≈ 544 tokens

  Planification capacitaire — Gapup agent-payable C-suite expertise (CHRO). Returns a structured, audited deliverable. Reference case: Gapup Hub — 22→48 FTE en 12m · ARR €480k→€1.7M · Plan d'embauches par département. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (7)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • company · object · requis
  • benchmarks · object · optionnel
  • financials · object · requis
  • constraints · array · optionnel
  • currentTeam · object · requis
  • hiringBudgetEur · number · optionnel

  Exemple d'appel

  {"name": "capacity_planning", "arguments": {"company": {}, "financials": {}, "currentTeam": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• capital_strategy≈ 681 tokens

  Stratégie de financement — Gapup agent-payable C-suite expertise (CSO). Returns a structured, audited deliverable. Reference case: Alan assurance santé SaaS — séquence Seed→A→B→C (2016-2022). Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • company · object · requis
  • growthPlan · object · requis
  • financialPosition · object · requis
  • founderConstraints · object · requis

  Exemple d'appel

  {"name": "capital_strategy", "arguments": {"company": {}, "growthPlan": {}, "financialPosition": {}, "founderConstraints": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• carbon_footprint_calculator≈ 1597 tokens

  Calculate a company's greenhouse-gas footprint under the GHG Protocol (Scope 1 + 2 + 3, in tCO2eq, tier-2 accuracy ±20%). Returns the emissions breakdown, hotspot identification, 5-8 reduction levers each with capex and payback, an SBTi-aligned reduction trajectory over 5-25 years, the 15 Scope-3 categories in detail, and CSRD/ESRS reporting readiness. When to use this tool: the user needs a carbon assessment for CSRD compliance pre-audit, green-finance access, or supplier ESG scorecards. Inputs: the company profile and its activity data. Delivered by Émilie, the AI Sustainability lead of the Gapup portfolio.

  Paramètres, retour & exemple (8)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • company · object · requis
  • perimeter · object · requis
  • scope1Sources · array · optionnel
  • scope2Sources · array · requis
  • reductionTargets · object · optionnel
  • scope3Activities · array · optionnel

  Exemple d'appel

  {"name": "carbon_footprint_calculator", "arguments": {"company": {}, "perimeter": {}, "scope2Sources": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"kpis": [], "hotspots": [], "breakdown": {}, "csrdReadiness": {}, "sbtiTrajectory": [], "reductionLevers": [], "executiveSummary": "texte", "scope3Categories": [], "totalEmissionsTco2eq": 1}}

• carbon_roadmap≈ 826 tokens

  Roadmap carbone — Gapup agent-payable C-suite expertise (SUSTAINABILITY). Returns a structured, audited deliverable. Reference case: Cas démo — Roadmap carbone. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (8)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • company · object · requis
  • perimeter · object · requis
  • scope1Sources · array · optionnel
  • scope2Sources · array · requis
  • reductionTargets · object · optionnel
  • scope3Activities · array · optionnel

  Exemple d'appel

  {"name": "carbon_roadmap", "arguments": {"company": {}, "perimeter": {}, "scope2Sources": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• champion_mapping≈ 486 tokens

  Cartographie du champion — Gapup agent-payable C-suite expertise (CRO). Returns a structured, audited deliverable. Reference case: Spendesk × Decathlon (deal €120k/an) — Champion identifié : CFO Group · Plan 6 semaines multi-touch. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (4)

  Paramètres

  • deal · object · requis
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • knownContacts · array · requis
  • sellerContext · object · requis

  Exemple d'appel

  {"name": "champion_mapping", "arguments": {"deal": {}, "knownContacts": [], "sellerContext": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• change_failure_root_cause_classifier≈ 522 tokens

  Classifies root causes of change failures for CTO-level incident analysis. Uses GitHub PR metadata and Snyk vulnerability data to identify patterns like dependency vulnerabilities, configuration drift, or deployment process gaps. Inputs include GitHub PR URL or incident ID, and outputs structured root cause categories with confidence scores. Ideal for post-mortem analysis and change risk assessment.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • pr_url · string · requis
  • incident_id · string · optionnel
  • snyk_org_id · string · optionnel
  • time_range_days · number · optionnel

  Exemple d'appel

  {"name": "change_failure_root_cause_classifier", "arguments": {"pr_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "root_causes": []}}

• china_ecommerce_intel≈ 1654 tokens

  Chinese e-commerce intelligence for the ZH diaspora (50M+), import-export teams, brand IP enforcement, MENA/Africa entrepreneurs sourcing from China, and brand monitoring. Covers Taobao, Tmall, JD.com, Pinduoduo, 1688.com (B2B) and AliExpress (cross-border). Five modes: • product_search — search products by keyword across CN platforms. Returns title ZH/EN, price CNY + USD estimate, sales 30d, rating, seller info, product URL. • seller_profile — full seller/supplier dossier: factory vs reseller detection, certifications (ISO, BSCI, CE), rating, years in business, main categories. • price_history — 12-month price trend for a product (live current price + seasonal model for CN shopping festivals: 11.11, 6.18, CNY). • brand_monitoring — detect counterfeits and grey market listings: price anomaly detection (>50% below MSRP = suspicious), counterfeit keyword scan, risk score 0-100. • market_intel — category overview: top 5 sellers by market share, avg/median price, volume estimate, price range. Data quality note: LIVE data from Taobao/Tmall/JD/Pinduoduo REQUIRES AICI_RESEARCH_PROXY_URL with CN residential routing (Bright Data -country-cn). Without proxy: AliExpress (cross-border) + curated category fallback available. Input formats for seller_profile: 'platform:id' e.g. 'aliexpress:123456', '1688:87654321', 'tmall:apple-store-official'. Input formats for price_history: AliExpress product URL or numeric product ID.

  Paramètres, retour & exemple (5)

  Paramètres

  • mode · string · requis · product_search | seller_profile | price_history | brand_monitoring | market_intel
    Analysis mode. product_search=find products, seller_profile=supplier dossier, price_history=price trend, brand_monitoring=counterfeit detection, market_intel=category overview.
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • query · string · requis
    Keyword, product name, product_id, seller_id (platform:id), brand name, or category. Accepts Chinese characters (ZH) or English.
  • region · string · optionnel · CN-domestic | cross-border
    Market region. CN-domestic=full platform coverage, cross-border=AliExpress+1688 focus. Default: CN-domestic.
  • platform · string · optionnel · taobao | tmall | jd | pinduoduo | 1688 | aliexpress | all
    Target platform. Default: all. Note: taobao/tmall/jd/pinduoduo require CN proxy.

  Exemple d'appel

  {"name": "china_ecommerce_intel", "arguments": {"mode": "product_search", "query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"mode": "texte", "status": "partial", "signals": [], "sources": [], "products": [], "market_intel": {}, "platform_used": [], "price_history": [], "quality_score": 1, "seller_profile": {}, "brand_monitoring": {}}}

• china_market_data≈ 1258 tokens

  Chinese capital market intelligence for the ZH diaspora (50M+) and institutional investors. Covers A-Shares (SSE/SZSE), H-Shares (HKEX), and ADRs across four modes: • company — full company profile: name ZH/EN, USCC (18-digit social credit code), exchange, industry (CSRC classification), chairperson, registered capital, SOE flag • market_quote — real-time quote: price (CNY or HKD), change%, volume, market cap, P/E ratio, dividend yield, last update timestamp • sector_overview — sector snapshot: top 5 companies by market cap, avg P/E, 30-day sector index change. Supported sectors: semiconductor, ev, battery, technology, finance, energy, realestate, consumer, pharma, telecom • regulatory_filing — recent regulatory disclosures (HKEX filings: annual, quarterly, announcements, mergers, IPOs) with title, date, document URL Input formats accepted: • 6-digit A-Share ticker (e.g. '600519' for Moutai SSE) • HKEX ticker (e.g. '0700.HK' or '700' for Tencent) • Company name in EN or ZH (e.g. '腾讯', 'Kweichow Moutai') • Sector keyword (e.g. 'semiconductor', '半导体') Data sources: Yahoo Finance (primary, always accessible), Eastmoney push2 + CompanySurvey (via Bright Data proxy when AICI_RESEARCH_PROXY_URL is set), HKEX filing API. Note: Eastmoney/CSRC/SSE are blocked from datacenter IPs without proxy — set AICI_RESEARCH_PROXY_URL to unlock full coverage.

  Paramètres, retour & exemple (5)

  Paramètres

  • mode · string · requis · company | market_quote | sector_overview | regulatory_filing
    Analysis mode. company=full profile, market_quote=price data, sector_overview=top 5 by sector, regulatory_filing=recent filings.
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • query · string · requis
    Ticker (6-digit A-share, 4-digit HK, Yahoo format), company name (ZH or EN), or sector keyword.
  • exchange · string · optionnel · SSE | SZSE | HKEX | all
    Exchange filter. Default: all. Affects sector_overview ticker selection.
  • period_days · number · optionnel
    Lookback period in days for regulatory filings. Default: 30.

  Exemple d'appel

  {"name": "china_market_data", "arguments": {"mode": "company", "query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"mode": "texte", "query": "texte", "status": "partial", "company": {}, "sources": [], "market_quote": {}, "quality_score": 1, "sector_overview": {}, "regulatory_filings": []}}

• churn_defender≈ 634 tokens

  Bouclier anti-churn — Gapup agent-payable C-suite expertise (CRO). Returns a structured, audited deliverable. Reference case: Spendesk — portefeuille 400 clients PME/ETI, détection churn Q2 2025 (€8M ARR). Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • company · object · requis
  • accounts · array · requis
  • csrContext · string · optionnel
  • analysisWindowDays · integer · requis

  Exemple d'appel

  {"name": "churn_defender", "arguments": {"company": {}, "accounts": [], "analysisWindowDays": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• climate_scenario_rcp≈ 1112 tokens

  Projections climatiques long terme par scénario IPCC (RCP AR5 + SSP AR6) pour toute localisation. Scénarios : RCP_4_5, RCP_8_5 (AR5), SSP1_2_6, SSP2_4_5, SSP3_7_0, SSP5_8_5 (AR6), ou 'all' (compare tous). Horizons : 2030–2100. Métriques : température (delta vs baseline 1990-2010, jours >35°C, nuits chaudes), précipitations (delta%, événements extrêmes, sécheresses), hausse du niveau de la mer (cm vs 2000), événements extrêmes (ouragans, inondations P100, sécheresses), indice incendie. Sorties : comparaison multi-scénarios, probabilité IPCC, signaux d'impact business par secteur. Sources : Open-Meteo CMIP6 (keyless), IPCC AR6 Atlas lookup, NOAA SLR projections. Usages : TCFD/CSRD physical risk, due diligence actifs long terme, assurance catastrophe, planification infrastructure. Cache 7j. SLA ≤20s.

  Paramètres, retour & exemple (6)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • metrics · array · optionnel
    Métriques à inclure. Défaut : toutes.
  • location · object · requis
    Localisation : {city, country?} ou {lat, lon}
  • scenario · string · requis · RCP_4_5 | RCP_8_5 | SSP1_2_6 | SSP2_4_5 | SSP3_7_0 | SSP5_8_5 | all
    Scénario IPCC. 'all' génère une comparaison multi-scénarios.
  • horizon_year · number · requis
    Année horizon de la projection (2030–2100)
  • compare_baseline · boolean · optionnel
    Comparer vs baseline 1990-2010 (défaut true)

  Exemple d'appel

  {"name": "climate_scenario_rcp", "arguments": {"location": {}, "scenario": "RCP_4_5", "horizon_year": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "partial", "sources": [], "location": {}, "scenario": "texte", "projections": {}, "horizon_year": 1, "quality_score": 1, "baseline_period": "texte", "ipcc_likelihood_label": "texte", "business_impact_signals": [], "multi_scenario_comparison": []}}

• clinical_evidence_briefer≈ 524 tokens

  Brief évidence clinique (GRADE) — Gapup agent-payable C-suite expertise (RISK). Returns a structured, audited deliverable. Answers: Review the clinical evidence for <drug/intervention> in <indication> — GRADE rating, key trials, safety signals. · Scan safety signals for <molecule> in <population> — adverse events, severity, frequency from FAERS and trial data. · Assess comparative effectiveness of <intervention> versus <comparator> for <disease> — what does the evidence show? · Is there evidence supporting drug repurposing of <molecule> for <new indication> — existing trials and GRADE quality? · What are the evidence gaps for <intervention> in <patient population> before formulary adoption? Reference case: Semaglutide 2.4mg · Chronic weight management in non-diabetic adults · GRADE high efficacy · studies found · nausea/GI signals · FDA approved · PubMed+ClinicalTrials+OpenFDA. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (8)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • topic · string · requis
  • max_studies · integer · requis
  • intervention · string · optionnel
  • evidence_focus · string · requis · efficacy | safety | adverse-events | comparative-effectiveness | all
  • target_disease · string · optionnel
  • date_range_years · integer · requis
  • intervention_type · string · optionnel · drug | device | biologic | procedure | behavioral | diagnostic

  Exemple d'appel

  {"name": "clinical_evidence_briefer", "arguments": {"topic": "texte", "max_studies": 1, "evidence_focus": "efficacy", "date_range_years": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• clinical_pharma_intel≈ 1493 tokens

  Clinical and pharmaceutical intelligence for biotech analysts, healthcare fund managers, pharma BD teams, catalyst-driven hedge funds and health journalists. Aggregates live data across five modes: • trials — active/completed clinical trials (ClinicalTrials.gov v2 + EU CTR in parallel, 450k+ records) • pipeline — full pipeline by sponsor: trial count by phase + top indications • approvals — FDA drug label approvals + mechanism of action (OpenFDA) • recalls — FDA enforcement recalls classified by severity (Class I/II/III) • adverse_events — FAERS aggregated reactions: top 10 reactions + serious% Signal detection (P0/P1/P2): P0 if Class I recall OR trial terminated for safety reason P1 if serious adverse events >30% OR ≥3 recalls in 12 months P2 otherwise (standard monitoring) All sources are public and keyless. Optional env OPENFDA_API_KEY raises daily quota from 1,000 to 120,000 requests. SLA: ≤16s p95 (parallel fetch, 8s budget per source). Cache: 6h trials, 24h approvals, 12h recalls, 6h adverse events.

  Paramètres, retour & exemple (7)

  Paramètres

  • mode · string · optionnel · trials | pipeline | approvals | recalls | adverse_events
    Analysis mode. Default "trials". trials=clinical trials, pipeline=sponsor overview, approvals=FDA approvals, recalls=enforcement, adverse_events=FAERS
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • phase · string · optionnel · 1 | 2 | 3 | 4 | NA
    Filter trials by phase (1/2/3/4/NA). Only applies to modes trials and pipeline.
  • query · string · requis
    Drug name, indication, sponsor or molecule (e.g. "atezolizumab", "metastatic NSCLC", "Roche", "semaglutide")
  • country · string · optionnel
    ISO 2-letter country code to filter trial sites (e.g. US, FR, DE).
  • max_results · number · optionnel
    Maximum number of results to return. Default 20.
  • status_filter · string · optionnel · recruiting | active | completed | terminated
    Filter trials by status. Only applies to modes trials and pipeline.

  Exemple d'appel

  {"name": "clinical_pharma_intel", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"mode": "texte", "query": "texte", "status": "partial", "trials": [], "recalls": [], "signals": [], "sources": [], "pipeline": {}, "approvals": [], "quality_score": 1, "adverse_events": {}}}

• cloud_cost_ri_optimizer≈ 451 tokens

  Analyzes AWS and Azure cloud pricing data alongside RIPE regional demand trends to generate Reserved Instance purchase recommendations for CTOs. Inputs include target cloud provider, instance family, region, and desired commitment term. Outputs include cost savings percentage, optimal RI quantity, and regional demand insights. Ideal for reducing cloud spend with data-driven decisions. Keywords: cloud cost optimization, reserved instances, AWS pricing, Azure pricing, RIPE demand trends.

  Paramètres, retour & exemple (6)

  Paramètres

  • term · string · optionnel · 1-year | 3-year
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • region · string · requis
  • utilization · number · optionnel
  • cloud_provider · string · requis · aws | azure
  • instance_family · string · requis

  Exemple d'appel

  {"name": "cloud_cost_ri_optimizer", "arguments": {"region": "texte", "cloud_provider": "aws", "instance_family": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "ri_cost": 1, "sources": [], "warnings": [], "on_demand_cost": 1, "break_even_months": 1, "regional_demand_score": 1, "cost_savings_percentage": 1, "recommended_ri_quantity": 1}}

• code_review_depth_optimizer≈ 537 tokens

  As a CTO, this tool analyzes your team's historical DORA metrics (deployment frequency, lead time, MTTR, change failure rate) and GitHub pull request data to recommend an optimal code review depth. Input your repository identifier and time range, and receive a structured recommendation on review rigor (light, standard, thorough) with supporting metrics and risk-adjusted rationale.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • teamSize · number · optionnel
    Number of active developers in the team
  • repository · string · requis
    GitHub repository identifier in format owner/repo
  • riskTolerance · string · optionnel · low | medium | high
    Organization's risk tolerance level
  • timeRangeDays · number · requis
    Number of days of historical data to analyze

  Exemple d'appel

  {"name": "code_review_depth_optimizer", "arguments": {"repository": "texte", "timeRangeDays": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "recommendation": {}}}

• comp_benchmark_geo_delta≈ 537 tokens

  Compares local compensation benchmarks against HQ standards for CHROs, adjusting for cost-of-living and tax differentials. Inputs include job role, local and HQ locations, and salary range. Outputs include adjusted benchmark delta, cost-of-living multiplier, and tax impact. Keywords: compensation benchmark, geographic pay equity, cost-of-living adjustment, tax differential analysis.

  Paramètres, retour & exemple (6)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • jobRole · string · requis
    Standardized job role (e.g., 'Software Engineer III')
  • currency · string · optionnel
    ISO 4217 currency code (e.g., 'USD')
  • baseSalary · number · optionnel
    Current base salary in local currency
  • hqLocation · string · requis
    HQ location (ISO 3166-2 code or city, country)
  • localLocation · string · requis
    Local work location (ISO 3166-2 code or city, country)

  Exemple d'appel

  {"name": "comp_benchmark_geo_delta", "arguments": {"jobRole": "texte", "hqLocation": "texte", "localLocation": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "taxImpact": 1, "adjustedSalary": 1, "benchmarkDelta": 1, "confidenceScore": 1, "costOfLivingMultiplier": 1}}

• comp_plan_architect≈ 622 tokens

  Architecture plan de commissionnement — Gapup agent-payable C-suite expertise (CRO). Returns a structured, audited deliverable. Reference case: Gapup Hub — Comp Plan 8 rôles commerciaux · OTE €65-280k · Budget comp €2.1M · Quota coverage 3.2×. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (7)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • company · object · requis
  • targets · object · requis
  • geography · string · optionnel
  • salesTeam · object · requis
  • currentChallenges · array · requis
  • preferredStructure · string · optionnel · base-plus-commission | ote-split | revenue-share | milestone-bonus | hybrid

  Exemple d'appel

  {"name": "comp_plan_architect", "arguments": {"company": {}, "targets": {}, "salesTeam": {}, "currentChallenges": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• competitive_deep_dive≈ 1388 tokens

  Gold-standard competitive deep dive — STRUCTURED multi-source data (no LLM narrative). Pair tool: `competitor_intel` for LLM-narrated board briefing + slide script. Aggregates Wikipedia, Yahoo Finance, SEC EDGAR, Wayback Machine, DuckDuckGo, HackerNews, domain scraping — all keyless. Returns agent-shaped JSON: KPIs (funding, employees, revenue, market cap), P0/P1/P2 competitive signals, pricing radar, competitor comparison matrix, Wayback timeline, positioning (sector/industry/icp_hypothesis/moat_signals), quality score. Every field is sourced or marked unavailable — no hallucinated figures. SLA: p50 ~25s, p95 ~30s · score 80+ on listed targets (US/EU/foreign) · score ~40 on private companies (no EDGAR/Yahoo data). Use sync for batch agents (≤30s tolerance). Use `competitive_deep_dive_async` + `competitive_deep_dive_result(job_id)` for conversational agents. Inputs: company name or domain (required), optional competitor list (≤5), optional depth (easy/medium/hard).

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • depth · string · optionnel · easy | medium | hard
    Research depth: 'easy' = Wikipedia + DDG (fast, ~15s); 'medium' = + Yahoo Finance + EDGAR + Wayback (default, ~45s); 'hard' = + HackerNews + domain surfaces + competitor deep dive (~120s)
  • company · string · requis
    Name or domain of the target company (e.g. 'Salesforce', 'notion.so', 'HubSpot CRM')
  • competitors · array · optionnel
    Optional list of competitor names or domains to include in the comparison matrix (max 5)

  Exemple d'appel

  {"name": "competitive_deep_dive", "arguments": {"company": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"kpis": [], "company": "texte", "quality": {}, "signals": [], "sources": [], "comparison": [], "depth_used": "easy", "positioning": {}, "generated_at": "texte", "pricing_radar": [], "domain_resolved": "texte", "wayback_timeline": []}}

• competitive_deep_dive_async≈ 478 tokens

  Async variant of competitive_deep_dive. Returns immediately (<200ms) with a job_id. The research runs in the background (p50≈25s, p95≈30s for depth=medium). Poll the result with competitive_deep_dive_result(job_id) after the eta_seconds hint. Use this instead of competitive_deep_dive when the agent cannot wait >15s for a response. Inputs: same as competitive_deep_dive — company (required), competitors (optional list, max 5), depth (easy/medium/hard, default medium). Async tool — register a webhook via `webhooks_manage(register, url, [job.completed])` to receive callbacks instead of polling. Faster + lighter.

  Paramètres, retour & exemple (3)

  Paramètres

  • depth · string · optionnel · easy | medium | hard
    Research depth: 'easy'≈15s, 'medium'≈30s (default), 'hard'≈60s
  • company · string · requis
    Name or domain of the target company (e.g. 'Salesforce', 'notion.so')
  • competitors · array · optionnel
    Optional list of competitor names or domains to include in the comparison matrix (max 5)

  Exemple d'appel

  {"name": "competitive_deep_dive_async", "arguments": {"company": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"job_id": "texte", "status": "queued", "eta_seconds": 1, "submitted_at": "texte"}}

• competitive_deep_dive_result≈ 373 tokens

  Poll the result of a competitive_deep_dive_async job. Returns status=pending while running, status=completed with the full report once done, status=failed on error, or status=not_found if the job_id is unknown or expired (TTL 24h). Call this after the eta_seconds hint returned by competitive_deep_dive_async.

  Paramètres, retour & exemple (1)

  Paramètres

  • job_id · string · requis
    The job_id returned by competitive_deep_dive_async

  Exemple d'appel

  {"name": "competitive_deep_dive_result", "arguments": {"job_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• competitor_intel≈ 1023 tokens

  LLM-narrated competitive-intelligence BRIEFING — for human consumption (board meeting, pitch prep). Pair tool: `competitive_deep_dive` for raw structured multi-source data (agent-shaped JSON). Returns: recent competitor moves with severity (critical/high/medium/low), prioritised signals, pricing-radar comparison, 3-6 quantified recommendations (impact in € or %, 7/30/90/180-day horizons), and an 8-12 slide presenter script. Use when the buyer wants a narrative briefing or a deck. Inputs: your company (name + one-paragraph pitch) + 1-10 competitors. Delivered by Manue, AI CMO of the Gapup portfolio.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
    Optional — what the buyer wants to track first (e.g. pricing moves, hiring patterns)
  • competitors · array · requis
    1-10 competitors to analyze
  • selfCompany · object · requis
    Your company info

  Exemple d'appel

  {"name": "competitor_intel", "arguments": {"competitors": [], "selfCompany": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"kpis": [], "sources": [], "pricingRadar": [], "competitorMoves": [], "presenterScript": [], "recommendations": [], "executiveSummary": "texte"}}

• competitor_moves≈ 364 tokens

  Mouvements concurrents — Gapup agent-payable C-suite expertise (CMO). Returns a structured, audited deliverable. Answers: What have my named competitors done recently — releases, pricing changes, hires, funding? · Which competitor signals are the most urgent right now and what should I do about them? Reference case: Notion — moves de ClickUp, Asana, Coda. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • competitors · array · requis
  • selfCompany · object · requis

  Exemple d'appel

  {"name": "competitor_moves", "arguments": {"competitors": [], "selfCompany": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• competitor_pricing_radar≈ 358 tokens

  Radar pricing concurrents — Gapup agent-payable C-suite expertise (CMO). Returns a structured, audited deliverable. Answers: How do my competitors' pricing plans and monthly prices compare to mine? · Which competitor plan undercuts or out-features my equivalent tier? Reference case: Notion — pricing vs ClickUp, Asana, Coda. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • competitors · array · requis
  • selfCompany · object · requis

  Exemple d'appel

  {"name": "competitor_pricing_radar", "arguments": {"competitors": [], "selfCompany": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• competitor_pricing_scrape≈ 560 tokens

  Scrape and parse a competitor pricing page from a URL or domain. Fetches via proxy-aware timedFetch (tries /pricing, /plans, homepage fallback), then extracts: plan names, prices, billing cadence (monthly/annual/usage-based/one-time), key features, free tier presence, enterprise tier, estimated price range. Returns structured pricing tiers. If unfetchable or no pricing found (anti-bot, SPA, auth wall): returns a clear degraded result with warnings and signals — never fake success. ICP: founders, product managers, pricing strategists, competitive intel teams. Proxy-aware (AICI_RESEARCH_PROXY_URL). Cache TTL 6h.

  Paramètres, retour & exemple (2)

  Paramètres

  • url · string · requis
    Competitor URL or domain (e.g. 'https://notion.so/pricing', 'notion.so', 'https://www.example.com'). For best results, provide the direct pricing page URL.
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.

  Exemple d'appel

  {"name": "competitor_pricing_scrape", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"tiers": [], "domain": "texte", "status": "partial", "warnings": [], "url_fetched": "texte", "has_free_tier": true, "pricing_found": true, "quality_score": 1, "raw_price_signals": [], "has_enterprise_tier": true, "plan_names_detected": [], "billing_model_signals": []}}

• competitor_profiles≈ 351 tokens

  Profils concurrents — Gapup agent-payable C-suite expertise (CMO). Returns a structured, audited deliverable. Answers: What are the strengths, weaknesses and positioning of each of my competitors? · Give me a SWOT-style profile of a named competitor. Reference case: Notion — profils de ClickUp, Asana, Coda. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • competitors · array · requis
  • selfCompany · object · requis

  Exemple d'appel

  {"name": "competitor_profiles", "arguments": {"competitors": [], "selfCompany": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• competitor_recommendations≈ 364 tokens

  Recommandations concurrentielles — Gapup agent-payable C-suite expertise (CMO). Returns a structured, audited deliverable. Answers: Given my competitors, what strategic actions should I take and in what order? · What should my 7/30/90/180-day competitive response plan look like? Reference case: Notion — actions face à ClickUp, Asana, Coda. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • competitors · array · requis
  • selfCompany · object · requis

  Exemple d'appel

  {"name": "competitor_recommendations", "arguments": {"competitors": [], "selfCompany": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• content_audience_profile≈ 510 tokens

  Return the audience targeting profile of a content entity — its enrichment tags reframed as audience facets with confidence, corroboration and full provenance (verifiable, sourced). The response also carries an entity-level provenance block (average confidence, data freshness). When to use this tool: an ad-tech or marketing agent needs a machine-readable, verifiable audience descriptor for a franchise or work. Input: an entity_id and its type.

  Paramètres, retour & exemple (3)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • entity_id · string · requis
    Entity id from content_catalog
  • entity_type · string · optionnel · franchise | work

  Exemple d'appel

  {"name": "content_audience_profile", "arguments": {"entity_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"entity_id": "texte", "provenance": {}, "entity_type": "texte", "audience_facets": {}}}

• content_catalog≈ 440 tokens

  Browse the Gapup gold-standard content catalogue — video games, films, TV series and music. Returns franchises with their works (title, release year). When to use this tool: an agent needs structured, audited metadata for a cultural franchise, wants to resolve a title to a canonical entity, or browses a domain's catalogue before requesting enrichment. Inputs: a content domain and an optional case-insensitive name filter. Each franchise id can be passed to content_enrichment for its fine-grained tag profile.

  Paramètres, retour & exemple (4)

  Paramètres

  • name · string · optionnel
    Optional case-insensitive substring filter on franchise name
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • limit · integer · optionnel
    Maximum number of franchises to return (default 20)
  • domain · string · requis · music | film | tv | video-game
    Content domain to browse

  Exemple d'appel

  {"name": "content_catalog", "arguments": {"domain": "music"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "domain": "texte", "franchises": []}}

• content_compare≈ 763 tokens

  Compare the tag profiles of two content entities (franchises or works) and measure how similar they are. Returns a Jaccard similarity score, the list of shared tags, the tags unique to each entity, and a breakdown of shared tags by facet. When to use this tool: an agent needs to compare two franchises or works (e.g. 'how similar are Dark Souls and Elden Ring?', 'what do Street Fighter and Mortal Kombat have in common?', 'on which axes do these two games differ?'), find positioning overlap, identify cross-sell opportunities, or answer 'if you liked X you might like Y' questions backed by data. Works for any domain (video-games, music, film, tv).

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • entity_a · string · requis
    Id of the first entity from content_catalog (e.g. 'game-dark-souls', 'music-daft-punk').
  • entity_b · string · requis
    Id of the second entity from content_catalog (e.g. 'game-elden-ring', 'music-justice').
  • entity_type · string · optionnel · franchise | work
    Whether both ids are franchises or works (applies to both). Defaults to 'franchise'.

  Exemple d'appel

  {"name": "content_compare", "arguments": {"entity_a": "texte", "entity_b": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"entity_a": "texte", "entity_b": "texte", "similarity": 1, "a_tag_count": 1, "b_tag_count": 1, "entity_type": "texte", "shared_tags": [], "unique_to_a": [], "unique_to_b": [], "shared_count": 1, "shared_by_facet": {}}}

• content_discovery≈ 681 tokens

  Discover content franchises within a domain. Two modes: pass `tag` for a precise taxonomy match (every game tagged 'co-op'), or pass `query` for free-text SEMANTIC search powered by pgvector embeddings — finding franchises by meaning ('dark atmospheric games about isolation') even when no literal tag matches. Results are verifiable: tag mode carries tag confidence/corroboration, semantic mode carries a similarity score; both carry entity freshness. When to use: an agent wants a domain-scoped shortlist by tag or by intent. Inputs: a domain plus either a tag or a free-text query.

  Paramètres, retour & exemple (5)

  Paramètres

  • tag · string · optionnel
    Tag label to match precisely (e.g. 'thriller', 'co-op'). Mutually exclusive with `query`.
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • limit · integer · optionnel
    Maximum franchises to return (default 25)
  • query · string · optionnel
    Free-text intent for semantic search (e.g. 'melancholic synth-pop about heartbreak'). Mutually exclusive with `tag`.
  • domain · string · requis · music | film | tv | video-game
    Content domain to search within

  Exemple d'appel

  {"name": "content_discovery", "arguments": {"domain": "music"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"tag": "texte", "count": 1, "query": "texte", "domain": "texte", "method": "tag", "franchises": []}}

• content_engine≈ 388 tokens

  Moteur de contenu — Gapup agent-payable C-suite expertise (CMO). Returns a structured, audited deliverable. Reference case: Notion — content engine 2026 (productivity B2B). Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • brand · object · requis
  • months · integer · requis
  • cluster · object · requis
  • maxArticlesPerMonth · integer · requis

  Exemple d'appel

  {"name": "content_engine", "arguments": {"brand": {}, "months": 1, "cluster": {}, "maxArticlesPerMonth": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• content_enrichment≈ 605 tokens

  Return the enriched tag profile of a content entity — the Gapup moat. Each tag carries a facet (genre, theme, play-mode, perspective…), a confidence score, a corroboration score and its full provenance (which sources corroborated it, when). The response also carries an entity-level provenance block (average confidence, data freshness). When to use this tool: an agent has a franchise or work id (from content_catalog) and needs a fine-grained, machine-readable, verifiable characterisation for matching, recommendation, contextual targeting or analysis. Inputs: an entity id and its type.

  Paramètres, retour & exemple (3)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • entity_id · string · requis
    Entity id from content_catalog (e.g. 'music-daft-punk', 'film-the-dark-knight-collection:the-dark-knight')
  • entity_type · string · optionnel · franchise | work
    Whether the id is a franchise or a work (default franchise)

  Exemple d'appel

  {"name": "content_enrichment", "arguments": {"entity_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"tags": [], "entity_id": "texte", "tag_count": 1, "provenance": {}, "entity_type": "texte"}}

• content_evergreen_score_analyzer≈ 470 tokens

  Evaluates content evergreen potential for CMOs by analyzing historical traffic patterns and backlink authority. Takes a content URL and optional time range, returns an evergreen score (0-100), traffic trend analysis, and backlink profile. Ideal for content strategy planning, SEO optimization, and identifying high-value evergreen assets. Uses Wayback Machine and Common Crawl public APIs.

  Paramètres, retour & exemple (4)

  Paramètres

  • url · string · requis
    Content URL to analyze
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • toDate · string · optionnel
    End date for historical analysis (YYYY-MM-DD)
  • fromDate · string · optionnel
    Start date for historical analysis (YYYY-MM-DD)

  Exemple d'appel

  {"name": "content_evergreen_score_analyzer", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "lastSeen": "texte", "warnings": [], "firstSeen": "texte", "trafficTrend": "declining", "backlinkCount": 1, "evergreenScore": 1, "backlinkDomains": 1}}

• content_provenance≈ 578 tokens

  Audit the full data provenance of a content entity — all its enrichment tags with their extraction source, corroboration score, source list and last verification date, plus an entity-level freshness summary. Use this tool before citing or relying on enriched content data in a high-stakes context (ad targeting, editorial, analysis). Inputs: entity_id (required) and entity_type (franchise or work).

  Paramètres, retour & exemple (3)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • entity_id · string · requis
    Entity id from content_catalog (e.g. 'video-game-elden-ring')
  • entity_type · string · optionnel · franchise | work
    Whether the id is a franchise or a work (default: franchise)

  Exemple d'appel

  {"name": "content_provenance", "arguments": {"entity_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"lineage": [], "entity_id": "texte", "entity_type": "texte", "freshness_summary": {}}}

• content_ranking≈ 760 tokens

  Return the TOP-ranked content entities in a category, by a chosen criterion — the direct answer to superlative / decision queries: 'best video games', 'top RPGs', 'cheapest games', 'best value RPGs', 'best FPS playable right now', 'most popular music artists'. Criteria: critic_score, popularity, price, value (critic score per unit price). `direction` flips it (asc = cheapest/lowest first). `available_only` restricts to entities currently buyable. Sliceable by genre and release-year window; every result carries its score, price and source. When to use: an agent must produce a ranked shortlist to support a recommendation, a purchase or a 'what is the best X' decision.

  Paramètres, retour & exemple (9)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • genre · string · optionnel
    Optional genre filter, e.g. 'RPG', 'FPS', 'thriller'
  • limit · integer · optionnel
    Number of ranked results (default 20)
  • domain · string · requis · music | film | tv | video-game
    Content domain to rank within
  • year_to · integer · optionnel
    Optional latest release year
  • criterion · string · optionnel · critic_score | popularity | price | value
    critic_score (0-100, default) · popularity · price · value (critic score per unit price)
  • direction · string · optionnel · desc | asc
    desc = best/highest first (default); asc = cheapest/lowest/least first. Defaults to asc for price.
  • year_from · integer · optionnel
    Optional earliest release year
  • available_only · boolean · optionnel
    If true, restrict to entities currently available to buy/play (default false)

  Exemple d'appel

  {"name": "content_ranking", "arguments": {"domain": "music"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "genre": "texte", "domain": "texte", "ranking": [], "year_to": 1, "criterion": "texte", "direction": "texte", "year_from": 1, "available_only": true}}

• content_similar≈ 615 tokens

  Find content entities similar to a given one. For embedded franchises this uses SEMANTIC vector similarity (pgvector) over the enrichment profile — surfacing entities that feel alike even when their tags differ literally. Falls back to shared enrichment-tag overlap for works or non-embedded entities. Each result carries a similarity score and its entity-level freshness/confidence (verifiable, sourced). When to use this tool: an agent wants recommendations or lookalikes for a franchise or work. Input: an entity_id and its type.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • limit · integer · optionnel
  • entity_id · string · requis
    Entity id from content_catalog
  • entity_type · string · optionnel · franchise | work

  Exemple d'appel

  {"name": "content_similar", "arguments": {"entity_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "method": "semantic", "similar": [], "entity_id": "texte", "source_provenance": {}}}

• content_taxonomy≈ 284 tokens

  Return the enrichment taxonomy of a content domain — every tag grouped by facet (genre, theme, mood, play-mode…). When to use this tool: an agent needs the controlled vocabulary to filter, classify or query content. Input: a domain.

  Paramètres, retour & exemple (2)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • domain · string · requis · music | film | tv | gaming
    Content domain

  Exemple d'appel

  {"name": "content_taxonomy", "arguments": {"domain": "music"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"domain": "texte", "taxonomy": {}, "tag_count": 1, "facet_count": 1}}

• contract_risk_scanner≈ 352 tokens

  Scanner de risques contractuels — Gapup agent-payable C-suite expertise (RISK). Returns a structured, audited deliverable. Reference case: Salesforce MSA — revue d'un client SaaS B2B EMEA. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • contractText · string · requis
  • contractContext · object · requis

  Exemple d'appel

  {"name": "contract_risk_scanner", "arguments": {"contractText": "texte", "contractContext": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• corporate_registry_lookup≈ 937 tokens

  Resolve legal information about a company from its national corporate registry. Returns a normalised, sourced company profile: legal status, registration number, directors, shareholders, recent filings, registered address, share capital, and a quality score (0–100). Coverage: France (INPI, keyless — full SIREN/SIRET with directors), 3M+ entities worldwide via GLEIF LEI (keyless, large companies), UK (Companies House, optional key), Netherlands (KvK, optional key), and OpenCorporates (token required since 2026). Sources are tried in cascade; quality_score increases with each source that succeeds. When to use: due-diligence, KYC screening, supplier verification, M&A research, or any workflow needing verified company identity and legal status. Optional env vars: COMPANIES_HOUSE_API_KEY (UK), KVK_API_KEY (NL), OPENCORPORATES_API_TOKEN (OpenCorporates token).

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • country · string · optionnel
    ISO 3166-1 alpha-2 country code (e.g. 'FR', 'GB', 'NL', 'DE', 'SG', 'AU', 'US'). If omitted, inferred from legal suffix in company name, then falls back to global search.
  • identifier · string · optionnel
    Optional registry identifier for a fast direct lookup: SIREN (FR, 9 digits), Companies House number (GB, 8 chars), KvK number (NL, 8 digits), etc.
  • company_name · string · requis
    Company name or trading name to look up (e.g. 'Sanofi', 'Tesco PLC', 'Notion Labs Inc')

  Exemple d'appel

  {"name": "corporate_registry_lookup", "arguments": {"company_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "active", "sources": [], "registry": "texte", "directors": [], "freshness": "texte", "identifier": "texte", "legal_form": "texte", "legal_name": "texte", "company_name": "texte", "jurisdiction": "texte", "shareholders": [], "quality_score": 1}}

• court_filings_multi≈ 1082 tokens

  Aggregate court filings, judgments and litigation records for a company or individual across five major legal jurisdictions: US (CourtListener / PACER), UK (National Archives — EWHC/EWCA/UKSC/UKUT), EU (ECHR HUDOC — European Court of Human Rights), France (Légifrance / Cour de cassation) and Germany (BGH / BVerfG). Returns structured case records with type classification (civil/criminal/antitrust/bankruptcy/administrative/unknown), status (filed/pending/decided/appealed/unknown), parties extracted from case titles, opinion URLs and verbatim snippets. Cross-case pattern recognition produces severity-ranked signals (P0–P2) for criminal, antitrust, bankruptcy, regulatory, data-breach and IP categories. Use when: due diligence on a counterparty, vendor risk assessment, competitive intelligence (litigation history), regulatory exposure mapping. All sources are public and keyless. Optional env var COURTLISTENER_API_KEY raises US rate limits beyond the default 5 req/s anonymous tier. SLA: ≤25s p95 (all jurisdictions fetched in parallel, 8s budget per source). Quality score: 20 pts per jurisdiction with ≥1 case retrieved, +10 if signals detected, +5–10 if ≥2–3 distinct sources contributed.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • date_to · string · optionnel
    ISO date YYYY-MM-DD — latest filing or decision date to include
  • date_from · string · optionnel
    ISO date YYYY-MM-DD — earliest filing or decision date to include
  • party_name · string · requis
    Name of the company or individual to search (e.g. "Apple Inc", "TotalEnergies", "Volkswagen AG")
  • jurisdiction · array · optionnel
    Jurisdictions to search. Defaults to all ["US","UK","EU","FR","DE"].

  Exemple d'appel

  {"name": "court_filings_multi", "arguments": {"party_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"cases": [], "status": "partial", "signals": [], "sources": [], "party_name": "texte", "quality_score": 1, "by_jurisdiction": {}, "jurisdictions_searched": []}}

• crm_connector≈ 586 tokens

  Push, update, search and log activities in HubSpot, Salesforce or Pipedrive. 4 modes: push_lead (create contact/lead), update_opportunity (update deal stage/amount), search_contact (lookup by email), log_activity (call/email/meeting/note). Returns resource_id, direct CRM URL, signals and quality_score. If credentials are absent, returns a mock result with a warning signal. Auth: HubSpot via Bearer access_token; Salesforce via access_token + base_url; Pipedrive via api_key.

  Paramètres, retour & exemple (5)

  Paramètres

  • data · object · requis
    Payload depending on mode. push_lead: {email,first_name,last_name,company,phone,job_title}. update_opportunity: {deal_id/opportunity_id,stage,amount,close_date}. search_contact: {email}. log_activity: {type,body,contact_id/person_id,subject}.
  • mode · string · requis · push_lead | update_opportunity | search_contact | log_activity
    Action to perform in the CRM
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • provider · string · requis · salesforce | hubspot | pipedrive
    CRM provider to target
  • credentials · object · optionnel
    Auth credentials. HubSpot: access_token. Salesforce: access_token + base_url. Pipedrive: api_key.

  Exemple d'appel

  {"name": "crm_connector", "arguments": {"data": {}, "mode": "push_lead", "provider": "salesforce"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"url": "texte", "mode": "texte", "status": "partial", "signals": [], "sources": [], "success": true, "provider": "texte", "data_synced": "texte", "resource_id": "texte", "quality_score": 1}}

• cross_sell_reco≈ 442 tokens

  Recommandations cross-sell — Gapup agent-payable C-suite expertise (CRO). Returns a structured, audited deliverable. Reference case: Alan × Gapup Hub — 3 produits recommandés · Fit 'perfect' × 2 · ARR potentiel +€18k. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • account · object · requis
  • company · object · requis
  • portfolio · array · requis

  Exemple d'appel

  {"name": "cross_sell_reco", "arguments": {"account": {}, "company": {}, "portfolio": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• crypto_wallet_intel≈ 1360 tokens

  Multi-chain on-chain analytics for crypto trading agents, on-chain analysts, AML/compliance teams and DeFi BD. Covers Ethereum, Base, Polygon, BSC, Arbitrum, Optimism — EVM-compatible addresses only. 5 modes: • wallet_profile — full wallet summary: type (EOA/contract/CEX/protocol), inferred persona (whale/MEV-bot/DeFi-user/hodler…), age, tx count, native balance, ERC-20 count, NFT collections, OFAC sanctions flag • token_flows — ERC-20 inflows/outflows per token on the selected period, priced in USD via CoinGecko • pnl_estimate — FIFO realized + unrealized P&L on the period with confidence rating (high/medium/low) • counterparties — top 20 counterparties ranked by USD volume with CEX/DEX/protocol labels • defi_positions — active DeFi positions detected via Etherscan interaction history (Aave/Compound/Uniswap/Curve/Lido/Balancer/SushiSwap) Signal detection (P0/P1/P2): P0 if OFAC SDN match OR direct Tornado Cash / sanctioned-protocol interaction P1 if >$1M volume on wallet <30 days old OR MEV-bot pattern OR >80% volume on single counterparty P2 informational (CEX wallet, new wallet, no anomaly) Sources: Etherscan family (keyless free-tier, optional API key per chain), DefiLlama (keyless), public EVM RPC (keyless), CoinGecko free tier (keyless). Cache TTL: 5 min (wallet activity evolves fast). Budget: 8s per source. Env vars (all optional, raise Etherscan rate-limit from 1 req/5s to 5 req/s): ETHERSCAN_API_KEY · BASESCAN_API_KEY · POLYGONSCAN_API_KEY BSCSCAN_API_KEY · ARBISCAN_API_KEY · OPTIMISM_API_KEY

  Paramètres, retour & exemple (6)

  Paramètres

  • mode · string · requis · wallet_profile | token_flows | pnl_estimate | counterparties | defi_positions
    Analysis mode. wallet_profile=full wallet summary + persona + sanctions flag. token_flows=ERC-20 inflows/outflows per token priced in USD. pnl_estimate=FIFO realized+unrealized P&L with confidence. counterparties=top 20 counterparties by volume. defi_positions=active positions on Aave/Compound/Uniswap/Curve/Lido/etc.
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • chain · string · optionnel · ethereum | base | polygon | bsc | arbitrum | optimism | all
    Chain to analyze. Default "ethereum". Use "all" to scan all 6 chains (slower, ~30s).
  • address · string · requis
    EVM-compatible wallet address (0x... 40 hex chars). Works on all supported chains.
  • period_days · number · optionnel
    Lookback window in days for token_flows, pnl_estimate, counterparties, defi_positions. Default 30.
  • min_value_usd · number · optionnel
    Minimum USD value filter for token_flows and counterparties. Default $100.

  Exemple d'appel

  {"name": "crypto_wallet_intel", "arguments": {"mode": "wallet_profile", "address": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"mode": "texte", "status": "texte", "address": "texte", "signals": [], "sources": [], "token_flows": [], "pnl_estimate": {}, "quality_score": 1, "counterparties": [], "defi_positions": [], "wallet_profile": {}, "chains_analyzed": []}}

• customer_marketing≈ 518 tokens

  Marketing clients & ambassadeurs — Gapup agent-payable C-suite expertise (CMO). Returns a structured, audited deliverable. Reference case: Gapup Hub — 12 clients analysés · 4 ambassadeurs identifiés · Programme + 6 case studies + référral. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (7)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • goals · array · requis
  • company · object · requis
  • product · object · requis
  • customers · array · requis
  • targetUseCases · array · optionnel
  • contentBudgetEur · number · optionnel

  Exemple d'appel

  {"name": "customer_marketing", "arguments": {"goals": [], "company": {}, "product": {}, "customers": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• customer_voice_synth≈ 408 tokens

  Synthèse voix client — Gapup agent-payable C-suite expertise (CMO). Returns a structured, audited deliverable. Reference case: Alan (assurance santé) — 3 personas · Top 5 douleurs · Repositionnement messagerie recommandé. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • company · object · requis
  • dataSources · array · requis
  • targetSegments · array · requis
  • repositioningFocus · string · optionnel

  Exemple d'appel

  {"name": "customer_voice_synth", "arguments": {"company": {}, "dataSources": [], "targetSegments": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• cve_security_lookup≈ 1150 tokens

  Look up CVE vulnerability data for enterprise security teams, DevSecOps and SOC analysts. Supports two modes: exact CVE ID lookup (e.g. 'CVE-2024-3094') or keyword search by product/vendor (e.g. 'openssl', 'Apache Tomcat'). Cross-references four authoritative keyless sources: NVD NIST (official CVE database, CVSS v3 scores, affected CPEs), CISA KEV (Known Exploited Vulnerabilities catalog — exploit_in_wild flag), EPSS FIRST (exploit probability 0-1), GitHub Security Advisories (ecosystem-specific: npm/pypi/maven). Returns structured vulnerability records with CVSS v3 scores, affected product version ranges, CWE weakness classification, references and exploitation status. Signals engine produces P0/P1/P2 alerts: P0=CVSS>=9 + active exploitation, P1=CVSS>=7 or EPSS>=70%, P2=CWE pattern clusters. Relevant for EU NIS2 and DORA supply chain risk obligations. Optional env: NVD_API_KEY (raises NVD rate-limit 5→50 req/30s), GITHUB_TOKEN (raises GHSA GraphQL rate-limit). Cache TTL 6h. SLA <=25s p95.

  Paramètres, retour & exemple (6)

  Paramètres

  • mode · string · optionnel · lookup | search
    Override auto-detection: "lookup" for exact CVE ID, "search" for product/vendor keyword.
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • query · string · requis
    CVE ID (e.g. "CVE-2024-3094") or product/vendor keyword (e.g. "openssl", "Apache Tomcat"). Mode is auto-detected from the CVE-YYYY-XXXXX pattern.
  • max_results · number · optionnel
    Maximum number of vulnerabilities to return (default 20, max 50).
  • severity_min · string · optionnel · low | medium | high | critical
    Minimum CVSS v3 severity to include in results (default: no filter).
  • published_after · string · optionnel
    ISO date YYYY-MM-DD — only include CVEs published after this date. Defaults to 365 days ago for search mode.

  Exemple d'appel

  {"name": "cve_security_lookup", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"mode": "lookup", "query": "texte", "status": "partial", "signals": [], "sources": [], "quality_score": 1, "vulnerabilities": []}}

• cyber_risk_auditor≈ 494 tokens

  Auditeur de risque cyber — Gapup agent-payable C-suite expertise (RISK). Returns a structured, audited deliverable. Reference case: Qonto — Audit cyber risque B2B FinTech · Score 58/100 → roadmap 90j · 8 findings critiques/high · économie prime -28%. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • company · object · requis
  • techStack · object · requis
  • currentPosture · object · requis

  Exemple d'appel

  {"name": "cyber_risk_auditor", "arguments": {"company": {}, "techStack": {}, "currentPosture": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• deal_coach≈ 392 tokens

  Coach de deal MEDDIC — Gapup agent-payable C-suite expertise (CRO). Returns a structured, audited deliverable. Reference case: Datadog Enterprise deal Société Générale €1.2M ARR — coaching MEDDIC + escalation plays + 14 next actions. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (5)

  Paramètres

  • deal · object · requis
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • knownContext · string · requis
  • buyingCommittee · array · requis

  Exemple d'appel

  {"name": "deal_coach", "arguments": {"deal": {}, "knownContext": "texte", "buyingCommittee": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• deal_structurer≈ 370 tokens

  Structuration de deal — Gapup agent-payable C-suite expertise (CSO). Returns a structured, audited deliverable. Reference case: Agicap × Kyriba — Partenariat API Banking · 5 structures comparées · Term sheet 7 clauses · Score 83/100 JV. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (3)

  Paramètres

  • deal · object · requis
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • company · object · requis

  Exemple d'appel

  {"name": "deal_structurer", "arguments": {"deal": {}, "company": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• dependency_vulnerability_scan≈ 1071 tokens

  SCA (Software Composition Analysis) — scans a project dependency manifest and returns known vulnerabilities for each dependency. Supports: package.json (npm), requirements.txt (Python), go.mod (Go), Cargo.toml (Rust), composer.json (PHP), Gemfile.lock (Ruby), CycloneDX SBOM JSON. PRIMARY source: OSV.dev (keyless, free, covers npm/PyPI/Go/crates.io/Packagist/RubyGems + GHSA advisories federated). CVSS enrichment: NVD NIST (when OSV lacks score). Exploitation flag: CISA KEV (known-exploited-vulnerabilities catalog). Returns per-vuln CVE/GHSA IDs, severity, CVSS score, fixed version, and actionable upgrade recommendations. Relevant for EU NIS2 supply chain risk obligations, DORA, SOC 2 vendor assessments. Cache TTL 6h. Parallel OSV queries (concurrency=10). SLA <=30s p95.

  Paramètres, retour & exemple (5)

  Paramètres

  • mode · string · requis · package_json | requirements_txt | go_mod | cargo_toml | composer_json | gem_lock | sbom_cyclonedx
    Manifest type: "package_json"=npm, "requirements_txt"=pip, "go_mod"=Go modules, "cargo_toml"=Rust, "composer_json"=PHP, "gem_lock"=Ruby, "sbom_cyclonedx"=CycloneDX SBOM JSON.
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • severity_min · string · optionnel · low | medium | high | critical
    Minimum severity to include in results (default: "medium").
  • manifest_content · string · requis
    Raw text content of the manifest file to scan (e.g. full contents of package.json, requirements.txt, etc.).
  • include_transitive · boolean · optionnel
    Include transitive/indirect dependencies in results (default: true).

  Exemple d'appel

  {"name": "dependency_vulnerability_scan", "arguments": {"mode": "package_json", "manifest_content": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"mode": "texte", "status": "partial", "sources": [], "summary": {}, "ecosystem": "npm", "quality_score": 1, "recommendations": [], "vulnerabilities": [], "dependencies_parsed": 1}}

• discovery_prep≈ 362 tokens

  Préparation discovery — Gapup agent-payable C-suite expertise (CRO). Returns a structured, audited deliverable. Reference case: Discovery Salesforce × Airbus — VP Digital Marc Legrand · Signaux achat confirmés · +28 pts conversion demo. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • contact · object · requis
  • ourOffer · string · requis
  • prospect · object · requis
  • meetingGoal · string · optionnel

  Exemple d'appel

  {"name": "discovery_prep", "arguments": {"contact": {}, "ourOffer": "texte", "prospect": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• diversity_inclusion_metrics≈ 526 tokens

  Métriques diversité & inclusion — Gapup agent-payable C-suite expertise (SUSTAINABILITY). Returns a structured, audited deliverable. Reference case: Cas démo — Métriques diversité & inclusion. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (6)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • company · object · requis
  • ambitions · string · requis
  • currentState · object · requis
  • regulatoryContext · array · optionnel

  Exemple d'appel

  {"name": "diversity_inclusion_metrics", "arguments": {"company": {}, "ambitions": "texte", "currentState": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• domain_tech_fingerprint≈ 407 tokens

  Empreinte tech d'un domaine — Gapup agent-payable C-suite expertise (CMO). Returns a structured, audited deliverable. Answers: What is the tech stack of <domain> — frontend, CMS, analytics, CRM, CDN, hosting? · What buying signals does <domain>'s technology footprint reveal for sales prospecting? · Analyze <domain> for supply-chain technology risk and third-party vendor exposure. · What is the best outreach angle for a sales rep targeting <domain> based on their detected stack? · Run a CISO-style technology fingerprint on <domain> — identify legacy tech, missing security headers, and vendor risk. · Has <domain> recently changed their marketing or analytics stack — any vendor adoption signals? Reference case: velora-payments.io · Next.js + Cloudflare + Stripe + GA4 + HubSpot · . Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • depth · string · requis · quick | standard | deep
  • focus · string · requis · tech-buying | supply-chain | general
  • target_domain · string · requis

  Exemple d'appel

  {"name": "domain_tech_fingerprint", "arguments": {"depth": "quick", "focus": "tech-buying", "target_domain": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• dora_metrics_deep_dive≈ 558 tokens

  Analyzes DORA metrics (Deployment Frequency, Mean Time to Recovery, Change Failure Rate) with deep correlation to code review patterns. Designed for CTOs to identify bottlenecks in software delivery pipelines. Inputs include GitHub repository identifiers and optional time ranges. Outputs structured metrics with trend analysis and code review depth insights.

  Paramètres, retour & exemple (5)

  Paramètres

  • repo · string · requis
    GitHub repository in format 'owner/repo'
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • since · string · optionnel
    Start date for analysis (ISO 8601)
  • until · string · optionnel
    End date for analysis (ISO 8601)
  • branch · string · optionnel
    Branch name to analyze (default: main)

  Exemple d'appel

  {"name": "dora_metrics_deep_dive", "arguments": {"repo": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "metrics": {}, "sources": [], "warnings": []}}

• dora_operational_resilience_stress_tes≈ 572 tokens

  Assess DORA operational resilience by simulating ICT failure scenarios for financial entities. Designed for legal/compliance teams to evaluate ICT risk management under DORA Article 25. Inputs include failure scenario parameters (e.g., ICT service type, duration, impact radius) and entity profile. Outputs structured resilience scores, regulatory gaps, and mitigation recommendations with EUR-Lex/FTC enforcement references.

  Paramètres, retour & exemple (6)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • entityType · string · requis · credit-institution | investment-firm | payment-institution | crypto-asset
  • impactRadius · string · requis · single-entity | multi-entity | sector-wide
  • ictServiceType · string · requis · cloud | network | payment | core | third-party
  • existingMitigations · array · optionnel
  • failureDurationHours · number · requis

  Exemple d'appel

  {"name": "dora_operational_resilience_stress_tes", "arguments": {"entityType": "credit-institution", "impactRadius": "single-entity", "ictServiceType": "cloud", "failureDurationHours": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "regulatoryGaps": [], "resilienceScore": 1, "simulationTimestamp": "texte", "recommendedMitigations": []}}

• dpdp_consent_artifact_generator≈ 662 tokens

  Generates structured consent artifacts compliant with India's Digital Personal Data Protection Act (DPDP). Designed for legal teams to verify or create consent records with timestamped logs, purpose limitation, and data subject rights. Accepts data subject details, processing purpose, and legal basis as inputs. Returns a signed artifact with audit trail and validation status.

  Paramètres, retour & exemple (6)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • legalBasis · string · requis · consent | contract | legal_obligation | vital_interests | public_task | legitimate_interests
    Legal basis for processing under DPDP
  • dataSubjectId · string · requis
    Unique identifier for the data subject
  • dataCategories · array · optionnel
    Categories of personal data being processed
  • processingPurpose · string · requis
    Specific purpose for data processing
  • retentionPeriodDays · number · optionnel
    Retention period in days

  Exemple d'appel

  {"name": "dpdp_consent_artifact_generator", "arguments": {"legalBasis": "consent", "dataSubjectId": "texte", "processingPurpose": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "artifact": {}, "warnings": []}}

• dual_use_export_risk_mapper≈ 514 tokens

  As a COO, quickly assess export compliance risks for components in your supply chain. This tool analyzes bills of materials (BOMs) against EU dual-use export control lists and ICAO/IMO restricted items data. Input a list of part numbers, descriptions, or HS codes to receive a risk assessment with actionable insights. Output includes risk levels, applicable regulations, and source references for audit trails.

  Paramètres, retour & exemple (3)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • bomItems · array · requis
  • includeSources · boolean · optionnel

  Exemple d'appel

  {"name": "dual_use_export_risk_mapper", "arguments": {"bomItems": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "results": [], "sources": [], "warnings": []}}

• dual_use_tech_diversion_monitor≈ 625 tokens

  Asynchronous T5-level tool for COO persona to detect unauthorized diversion of dual-use technologies. Cross-references shipment manifests, EU sanctions lists, and ICAO/IMO transport data to identify suspicious transfers. Inputs: shipment IDs, company identifiers, or geographic routes. Outputs structured diversion risk assessment with source provenance. Requires async:true to avoid 402 timeout.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • route · object · optionnel
  • companyId · string · optionnel
    Company registration number or tax identifier
  • shipmentId · string · optionnel
    Unique shipment identifier (e.g., bill of lading number)
  • techCategory · string · optionnel · aerospace | nuclear | biotech | semiconductors | telecom
    Dual-use technology category

  Exemple d'appel

  {"name": "dual_use_tech_diversion_monitor", "arguments": {"async": true, "route": {}, "companyId": "texte", "shipmentId": "texte", "techCategory": "aerospace"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "matches": [], "sources": [], "warnings": [], "diversionRisk": 1}}

• earnings_reviewer≈ 387 tokens

  Earnings Reviewer — Gapup agent-payable C-suite expertise (FUNDRAISING). Returns a structured, audited deliverable. Reference case: Salesforce Q3 FY2026 — call transcript + 10-Q + guidance → analyst note. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (6)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • company · object · requis
  • quarter · object · requis
  • analystFocus · string · optionnel
  • secFilingContext · string · optionnel
  • transcriptExcerpt · string · requis

  Exemple d'appel

  {"name": "earnings_reviewer", "arguments": {"company": {}, "quarter": {}, "transcriptExcerpt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• earnings_transcript_signals≈ 594 tokens

  Earnings call transcript signal extractor for equity research analysts, catalyst-driven hedge funds, and BD teams. Parses earnings transcripts (fetched or provided) to surface: • signals (P0/P1/P2): guidance raise/cut, miss/beat vs consensus, buyback, dividend change, new product, executive change, capex shift, M&A intent, regulatory risk, competitive threat, supply chain, hiring • kpis_mentioned: Revenue, EBITDA, EPS, FCF, Gross Margin, Operating Margin with YoY/QoQ % • guidance: raised / maintained / cut / new_initiated items extracted • q_and_a_topics: top Q&A themes detected (AI strategy, China exposure, M&A pipeline, macro, etc.) • overall_tone: bullish / neutral / bearish Sources fetched automatically: SEC EDGAR 8-K filings, Yahoo Finance earnings news, Motley Fool transcripts. If no transcript can be retrieved from any source, returns status:'failed' with an explicit warning and empty signals — never fabricated data. Accepts transcript_text override for direct analysis. Supports multilingual transcripts (de/fr/es/zh). European tickers (SAP.DE, BMW.DE) mapped to EDGAR-compatible equivalents automatically.

  Paramètres, retour & exemple (5)

  Paramètres

  • lang · string · optionnel · en | de | fr | es | zh
    Language hint for the transcript. Affects mock transcript language when fetch fails.
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • quarter · string · optionnel
    Fiscal quarter in format Q1-2026. Defaults to the most recent past quarter.
  • transcript_text · string · optionnel
    If provided, skips all external fetches and analyses this text directly. Minimum 100 characters.
  • company_or_ticker · string · requis
    Company name or ticker symbol (e.g. 'Tesla', 'TSLA', 'SAP', 'SAP.DE', 'Sanofi', 'SNY'). European tickers (SAP.DE, BMW.DE) are mapped to their ADR equivalents for EDGAR lookup.

  Exemple d'appel

  {"name": "earnings_transcript_signals", "arguments": {"company_or_ticker": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• economic_indicator≈ 363 tokens

  Return a precise macroeconomic indicator for a country — the exact figure for a market-sizing, finance or strategy workflow. Indicators: gdp_usd, gdp_per_capita, gdp_growth, inflation, unemployment, population. Source: World Bank. When to use: an agent's analysis needs an authoritative country-level economic figure. Inputs: country (ISO-2 or ISO-3 code) and indicator name.

  Paramètres, retour & exemple (3)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • country · string · requis
    Country code, ISO-2 or ISO-3 (e.g. FR, USA)
  • indicator · string · requis · gdp_usd | gdp_per_capita | gdp_growth | inflation | unemployment | population
    Macroeconomic indicator name

  Exemple d'appel

  {"name": "economic_indicator", "arguments": {"country": "texte", "indicator": "gdp_usd"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"year": "texte", "value": 1, "source": "texte", "country": "texte", "indicator": "texte", "source_url": "texte", "indicator_code": "texte"}}

• email_domain_health_check≈ 1173 tokens

  Comprehensive email domain health check: MX routing, SPF authentication, DKIM signing, DMARC policy enforcement, DNSBL blacklist status (Spamhaus/SpamCop/Barracuda), TLS certificate validity, and WHOIS registration age. Aggregates a reputation score 0-100 and generates P0/P1/P2 deliverability signals. Accepts a domain (stripe.com) or email address (info@stripe.com). Detects role-based addresses (info@, support@, admin@, noreply@) that have higher bounce rates. Detects email provider (Google Workspace, Microsoft 365, Amazon SES, etc.). P0 signals: blacklisted / no MX / TLS expired / no SPF + DMARC none. P1 signals: SPF soft-fail / no DKIM selector / DMARC no reporting. P2 signals: role-based address / TLS expires <30d / domain age <90 days. All checks are keyless (no API keys required). Cache TTL 1h. SLA <=10s p95.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • email · string · optionnel
    Full email address for additional checks: format validity, role-based detection (e.g. "ceo@stripe.com").
  • checks · array · optionnel
    Subset of checks to run. Defaults to all 8: ["mx","spf","dkim","dmarc","blacklist","whois","tls","reputation"]. Use a subset for faster responses (e.g. ["mx","spf","dmarc","reputation"] for quick scoring).
  • domain · string · requis
    Domain to check (e.g. "stripe.com" or "@stripe.com"). If an email address is provided here, the domain is extracted automatically.

  Exemple d'appel

  {"name": "email_domain_health_check", "arguments": {"domain": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"mx": {}, "spf": {}, "tls": {}, "dkim": {}, "dmarc": {}, "whois": {}, "domain": "texte", "status": "partial", "sources": [], "blacklist": {}, "email_valid": true, "quality_score": 1}}

• enps_auto≈ 780 tokens

  eNPS automatisé — Gapup agent-payable C-suite expertise (CHRO). Returns a structured, audited deliverable. Reference case: BlaBlaCar — eNPS pulse mensuel · 700 FTE 8 pays · segments × tenure × manager · plays correctifs ciblés. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (7)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • company · object · requis
  • context · object · requis
  • toolStack · object · requis
  • segmentation · object · requis
  • presenterScript · array · optionnel

  Exemple d'appel

  {"name": "enps_auto", "arguments": {"company": {}, "context": {}, "toolStack": {}, "segmentation": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• esg_audit_multi≈ 1206 tokens

  Multi-mode ESG intelligence for ESG analysts, sustainability officers and impact investing fund managers. Aggregates live data from CDP, SBTi, Wikipedia, Yahoo Finance and web search across five modes: • company_score — ESG score 0-100 with E/S/G breakdown + heuristic rating (AAA-CCC), from CDP grade + SBTi + sector profile • controversy_check — controversies detected via web search, classified P0/P1/P2 by type (greenwashing, emissions fraud, labour, governance) • emissions — GHG Scope 1/2/3 estimates, SBTi validation flag, net-zero target year, carbon intensity per M€ revenue • esrs_readiness — CSRD gap across 12 standards (E1-E5, S1-S4, G1-G3): readiness % + gap list + CSRD deadline + effort man-days • sfdr_classification — suggested SFDR Article 6/8/9 with rationale and sustainability indicators met Signals: P0=critical (controversy/score<40), P1=significant (score<55/SBTi missing/ESRS<50%), P2=watch. Cache 24h.

  Paramètres, retour & exemple (5)

  Paramètres

  • mode · string · requis · company_score | controversy_check | emissions | esrs_readiness | sfdr_classification
    Analysis mode.
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • query · string · requis
    Company name, ticker, ISIN or LEI (e.g. "Microsoft", "Sanofi", "Volkswagen").
  • pillar · string · optionnel · E | S | G | all
    ESG pillar filter (optional, default: all).
  • framework · string · optionnel · GRI | SASB | TCFD | ESRS | all
    ESG framework filter (optional, default: all).

  Exemple d'appel

  {"name": "esg_audit_multi", "arguments": {"mode": "company_score", "query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"mode": "texte", "status": "partial", "signals": [], "sources": [], "emissions": {}, "company_score": {}, "controversies": [], "quality_score": 1, "esrs_readiness": {}, "sfdr_classification": {}}}

• esrs_narrative_builder≈ 707 tokens

  Architecte du narratif ESRS / CSRD — Gapup agent-payable C-suite expertise (SUSTAINABILITY). Returns a structured, audited deliverable. Reference case: L'Oréal France — narratif ESRS E1+E5 + S1 + G1 · CSRD reporting 2025-2026 · double-matérialité chiffrée. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (6)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • scope · object · requis
  • company · object · requis
  • context · object · requis
  • presenterScript · array · optionnel

  Exemple d'appel

  {"name": "esrs_narrative_builder", "arguments": {"scope": {}, "company": {}, "context": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• event_marketing≈ 454 tokens

  Marketing événementiel — Gapup agent-payable C-suite expertise (CMO). Returns a structured, audited deliverable. Reference case: Pennylane (€120k/an budget événements) — 7 événements sélectionnés · coût-MQL -38% vs année précédente. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (8)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • company · object · requis
  • teamSize · number · requis
  • geography · array · requis
  • objectives · array · requis
  • currentEvents · array · requis
  • targetAudience · string · requis
  • annualBudgetEur · number · requis

  Exemple d'appel

  {"name": "event_marketing", "arguments": {"company": {}, "teamSize": 1, "geography": [], "objectives": [], "currentEvents": [], "targetAudience": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• executive_comp_peer_benchmark≈ 558 tokens

  As a Chief Human Resources Officer (CHRO), benchmark executive compensation packages against peer companies using public SEC filings and private compensation data from Equilar and Bloomberg. Inputs include executive name, title, company ticker, and peer group criteria. Outputs structured compensation metrics (base salary, bonus, equity, total compensation) with source attribution and confidence scores.

  Paramètres, retour & exemple (6)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • peerGroup · object · optionnel
  • fiscalYear · number · optionnel
  • companyTicker · string · requis
  • executiveName · string · requis
  • executiveTitle · string · requis

  Exemple d'appel

  {"name": "executive_comp_peer_benchmark", "arguments": {"companyTicker": "texte", "executiveName": "texte", "executiveTitle": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "compensation": {}}}

• financial_model_3statement≈ 1052 tokens

  Pure-compute 3-statement financial model builder (Income Statement + Balance Sheet + Cash Flow). Feed assumptions (revenue growth, COGS%, OpEx, CapEx, working capital, tax rate, depreciation, debt schedule) → receive a full 3-5 year projection with integrated DCF valuation. Supports IFRS / US_GAAP / PRC_GAAP (中国会计准则) norms with bilingual ZH+EN labels for PRC. Modes: build (full 3-statement model) | scenario_analysis (base/bull/bear ±20% growth) | sensitivity (1 KPI × 1 input, 5-point grid). No external data needed — all computed from assumptions. ICP: VC due diligence, M&A analysts, CFO SMB, startup founders pitching investors, biotech/SaaS modeling. Returns balance_check_ok per year, DCF enterprise/equity value, and coherence warnings.

  Paramètres, retour & exemple (5)

  Paramètres

  • mode · string · requis · build | scenario_analysis | sensitivity
    build = full 3-statement model | scenario_analysis = base/bull/bear | sensitivity = 1 KPI × 1 input
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • assumptions · object · requis
    Financial assumptions for the model
  • sensitivity_kpi · string · optionnel · revenue_y3 | ebitda_y3 | fcf_y3 | cash_y3 | valuation
    KPI to observe in sensitivity mode.
  • sensitivity_input · string · optionnel
    Assumption param to vary in sensitivity mode. E.g. 'growth_rates_pct[0]' or 'cogs_pct_of_revenue'.

  Exemple d'appel

  {"name": "financial_model_3statement", "arguments": {"mode": "build", "assumptions": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"mode": "texte", "norms": "texte", "status": "partial", "sources": [], "warnings": [], "cash_flow": {}, "scenarios": {}, "sensitivity": [], "balance_sheet": {}, "quality_score": 1, "valuation_dcf": {}, "income_statement": {}}}

• fraud_detector≈ 426 tokens

  Détecteur de fraude — Gapup agent-payable C-suite expertise (RISK). Returns a structured, audited deliverable. Reference case: TechManu SAS — Industriel FR €32M CA, 148 FTE · 30j · 21 anomalies · €487k à risque. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • company · object · requis
  • analysisPeriodDays · integer · requis
  • transactionVolumes · object · requis

  Exemple d'appel

  {"name": "fraud_detector", "arguments": {"company": {}, "analysisPeriodDays": 1, "transactionVolumes": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ftg_business_ideas≈ 251 tokens

  Return vetted, automation-scored business ideas from the FTG idea bank — each with an autonomy score, monetization model and conservative/median/optimistic MRR projections. When to use this tool: an agent or founder wants ranked, buildable business ideas. Input: optional category and limit.

  Paramètres, retour & exemple (3)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • limit · integer · optionnel
  • category · string · optionnel
    Optional category filter

  Exemple d'appel

  {"name": "ftg_business_ideas", "arguments": {"async": true, "limit": 1, "category": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "ideas": []}}

• ftg_business_plan≈ 327 tokens

  Return the business plan for a market-gap opportunity — direct-trade or local-production, with CAPEX, OPEX, ROI, payback period, automation level and the full plan. Cache-first: returns the stored plan when available, otherwise reports that generation is required (the FTG platform produces plans on demand). When to use this tool: an agent has an opportunity_id (from ftg_market_gap) and needs the investable plan. Input: an opportunity_id.

  Paramètres, retour & exemple (2)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • opportunity_id · string · requis
    Opportunity id obtained from ftg_market_gap

  Exemple d'appel

  {"name": "ftg_business_plan", "arguments": {"opportunity_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"plans": [], "status": "ready", "message": "texte", "plan_count": 1, "opportunity_id": "texte"}}

• ftg_country_regulations≈ 277 tokens

  Return import, trade and production regulations for a country — category, title, summary and source. When to use this tool: an agent checks regulatory or compliance requirements before trading or producing in a market. Input: a country, with an optional category.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • limit · integer · optionnel
  • country · string · requis
    Country ISO code or name
  • category · string · optionnel
    Optional regulation category filter

  Exemple d'appel

  {"name": "ftg_country_regulations", "arguments": {"country": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "regulations": []}}

• ftg_country_study≈ 250 tokens

  Return the in-depth FTG country study — multi-part structured analysis of a country's trade and production landscape. When to use this tool: an agent needs deep country context before a sourcing, export or investment decision. Input: a country.

  Paramètres, retour & exemple (2)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • country · string · requis
    Country ISO code or name

  Exemple d'appel

  {"name": "ftg_country_study", "arguments": {"country": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "parts": [], "country": "texte", "part_count": 1}}

• ftg_investor_directory≈ 245 tokens

  Return investors from the FTG directory — VC, PE and impact funds with type, firm, website, ticket-size range, sectors and stages of interest. When to use this tool: an agent builds a fundraising shortlist. Input: optional country and limit.

  Paramètres, retour & exemple (3)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • limit · integer · optionnel
  • country · string · optionnel
    Optional country ISO code or name

  Exemple d'appel

  {"name": "ftg_investor_directory", "arguments": {"async": true, "limit": 1, "country": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "investors": []}}

• ftg_market_gap≈ 436 tokens

  Return the import/production market-gap opportunities for a country — commodities where local demand outpaces local supply. Each opportunity carries the gap value (USD/year), the gap volume (tonnes/year), a 0-100 opportunity score and the potential margin. When to use this tool: an agent needs to know what a country structurally under-produces or over-imports, for trade sourcing, import/export or local-production investment decisions. Input: a country (ISO-2 code or name).

  Paramètres, retour & exemple (3)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • limit · integer · optionnel
    Maximum opportunities to return (default 20)
  • country · string · requis
    Country ISO-2 code (e.g. 'SN', 'KE') or name (e.g. 'Senegal')

  Exemple d'appel

  {"name": "ftg_market_gap", "arguments": {"country": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "country": "texte", "opportunities": []}}

• ftg_opportunity_scout≈ 362 tokens

  Rank the best countries for a given commodity — where the market gap, opportunity score and potential margin are highest. Cross-country scouting. When to use this tool: an agent has a commodity and needs to know WHERE to sell, export to or set up local production. Input: a commodity name.

  Paramètres, retour & exemple (3)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • limit · integer · optionnel
    Maximum countries to return (default 20)
  • commodity · string · requis
    Commodity name (e.g. 'rice', 'soybean', 'poultry')

  Exemple d'appel

  {"name": "ftg_opportunity_scout", "arguments": {"commodity": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "count": 1, "commodity": "texte", "countries": []}}

• ftg_production_economics≈ 307 tokens

  Return production cost benchmarks (CAPEX/OPEX per unit, value ranges, scenarios, quality tiers) and agronomic yields (t/ha, cycles per year) for a commodity. When to use this tool: an agent sizes the economics of producing a commodity. Input: a commodity, with an optional country.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • limit · integer · optionnel
  • country · string · optionnel
    Optional country ISO code or name
  • commodity · string · requis
    Commodity name or slug

  Exemple d'appel

  {"name": "ftg_production_economics", "arguments": {"commodity": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"yields": [], "commodity": "texte", "cost_benchmarks": []}}

• ftg_production_methods≈ 305 tokens

  Return the production methods for a commodity — each with a description, ordered process steps, pros/cons and a popularity rank. Methods are commodity-canonical: one curated set per commodity, reusable across every country. When to use this tool: an agent evaluates HOW a commodity is produced or processed, compares techniques, or builds a production plan. Input: a commodity slug or name.

  Paramètres, retour & exemple (2)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • commodity · string · requis
    Commodity slug or name (e.g. 'rice', 'tomato', 'cashew')

  Exemple d'appel

  {"name": "ftg_production_methods", "arguments": {"commodity": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "methods": [], "commodity": "texte", "method_count": 1}}

• ftg_seller_catalog≈ 270 tokens

  Return seller catalogues registered on FTG — exporters and producers with their commodity, monthly capacity, certifications and target export markets. When to use this tool: an agent builds a supplier or sourcing shortlist. Input: optional seller country and commodity.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • limit · integer · optionnel
  • country · string · optionnel
    Optional seller country ISO code or name
  • commodity · string · optionnel
    Optional commodity filter

  Exemple d'appel

  {"name": "ftg_seller_catalog", "arguments": {"async": true, "limit": 1, "country": "texte", "commodity": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "sellers": []}}

• ftg_sourcing_buyers≈ 332 tokens

  Return verified local buyers in a country — companies sourcing a given commodity, with buyer type, city, website, annual volume range and certification requirements. When to use this tool: an agent builds a sourcing or export shortlist, or needs real B2B demand contacts in a market. Input: a country and an optional commodity filter.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • limit · integer · optionnel
    Maximum buyers to return (default 20)
  • country · string · requis
    Country ISO-2 code or name
  • commodity · string · optionnel
    Optional commodity slug to filter buyers by

  Exemple d'appel

  {"name": "ftg_sourcing_buyers", "arguments": {"country": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"buyers": [], "country": "texte", "commodity": "texte", "buyer_count": 1}}

• funding_hunter≈ 637 tokens

  Chasseur de financements — Gapup agent-payable C-suite expertise (CFO). Returns a structured, audited deliverable. Reference case: PME deeptech cleantech FR €8M CA — top 30 dispositifs BPI+France2030+EU+VC. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • company · object · requis
  • project · object · requis
  • financials · object · requis
  • preferences · object · requis

  Exemple d'appel

  {"name": "funding_hunter", "arguments": {"company": {}, "project": {}, "financials": {}, "preferences": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• fx_rate≈ 393 tokens

  Get the current or historical foreign-exchange rate for any currency pair — the exact exchange rate, FX rate or conversion rate an agent needs to convert a currency amount or feed a finance, trading, invoicing or pricing workflow. Covers EUR/USD, USD/JPY, GBP/EUR and every ISO-4217 currency pair. Returns the latest spot rate, or a historical rate by date. Use when a workflow needs a precise live or past currency exchange rate, or to convert money between two currencies. Source: European Central Bank reference rates via Frankfurter. Inputs: from/to ISO-4217 currency codes, optional date (YYYY-MM-DD).

  Paramètres, retour & exemple (4)

  Paramètres

  • to · string · requis
    Quote currency, ISO-4217 (e.g. USD)
  • date · string · optionnel
    Optional YYYY-MM-DD for a historical rate
  • from · string · requis
    Base currency, ISO-4217 (e.g. EUR)
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.

  Exemple d'appel

  {"name": "fx_rate", "arguments": {"to": "texte", "from": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"to": "texte", "from": "texte", "rate": 1, "as_of": "texte", "source": "texte", "source_url": "texte"}}

• geo_logistics_intel≈ 1096 tokens

  Geospatial logistics intelligence for supply chain, maritime and transport agents. Four modes: (1) geocode_batch — resolve up to 50 addresses to lat/lon with confidence scores (OSM Nominatim + Open-Meteo fallback, 1 req/s rate-limit respected); (2) routing — road/cycling/walking route with distance_km, duration_seconds and ETA ISO timestamp between two addresses or lat/lon points (OSRM public, keyless, global); (3) port_congestion — congestion status for any UN/LOCODE port (e.g. NLRTM, SGSIN, CNSHA) with waiting vessel count, severity (low/medium/high/extreme) and average wait hours; (4) ship_tracking — AIS position, speed, course, destination and ETA for a vessel by its 9-digit MMSI. No API key required for geocode/routing/port. Optional env: AIS_STREAM_API_KEY for live ship data (otherwise MarineTraffic scrape best-effort). SLA: <=25s p95. Cache: 24h geocoding / 1h routing / 30min port / 5min ship. Quality score 0-100. Status: final/partial/failed.

  Paramètres, retour & exemple (7)

  Paramètres

  • to · string · optionnel
    routing only: destination address or 'lat,lon'
  • from · string · optionnel
    routing only: origin address or 'lat,lon'
  • mode · string · requis · geocode_batch | routing | port_congestion | ship_tracking
    'geocode_batch': address -> lat/lon. 'routing': route + ETA. 'port_congestion': UN/LOCODE port state. 'ship_tracking': vessel by MMSI
  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • query · string · requis
    Primary input: address for geocode/routing, UN/LOCODE (e.g. NLRTM) for port_congestion, 9-digit MMSI for ship_tracking
  • addresses · array · optionnel
    geocode_batch only: up to 50 addresses (overrides query if provided)
  • mode_transport · string · optionnel · driving | walking | cycling
    routing only: transport mode. Default: driving

  Exemple d'appel

  {"name": "geo_logistics_intel", "arguments": {"mode": "geocode_batch", "query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"mode": "texte", "status": "partial", "routing": {}, "sources": [], "geocode_batch": [], "quality_score": 1, "ship_tracking": {}, "port_congestion": {}}}

• geographic_expansion≈ 597 tokens

  Expansion géographique — Gapup agent-payable C-suite expertise (CSO). Returns a structured, audited deliverable. Reference case: Gapup Hub — Expansion 4 marchés (DE/UK/ES/NL) · €1.8M budget · ARR cible €3.2M Y2. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (8)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • company · object · requis
  • product · object · requis
  • financials · object · optionnel
  • constraints · array · optionnel
  • targetMarkets · array · requis
  • preferredEntryMode · string · optionnel · direct-sales | partnership | acquisition | distributor | greenfield
  • expansionHorizonMonths · integer · optionnel

  Exemple d'appel

  {"name": "geographic_expansion", "arguments": {"company": {}, "product": {}, "targetMarkets": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• gl_reconciler≈ 536 tokens

  GL Reconciler — Réconciliation grand livre — Gapup agent-payable C-suite expertise (CFO). Returns a structured, audited deliverable. Answers: Identify the root causes of the <N> GL breaks in <company>'s ledger for <period> — cluster them and rank by materiality. · For <company> Q<X> close: which accounts have unreconciled items over €<threshold>? Provide a sign-off routing and resolution plan. · Run an automated GL reconciliation for <company> — AR/AP/intercompany entries — flag open items, suggest journal entries. · What are the top 5 systemic control weaknesses causing recurring GL breaks at <company>? Recommend preventive controls. · Generate a month-end close reconciliation report for <company> <period> — breaks by account type, aging analysis, sign-off assignments. Reference case: Acme SaaS Q4 2026 — 47 breaks GL, €1.4M variance non postée. Inputs are validated server-side — send the documented case fields.

  Paramètres, retour & exemple (4)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • focus · string · optionnel
  • entity · object · requis
  • ledgerContext · object · requis

  Exemple d'appel

  {"name": "gl_reconciler", "arguments": {"entity": {}, "ledgerContext": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• global_salary_inflation_adjuster≈ 381 tokens

  Adjusts salary benchmarks for local inflation using OECD, IMF, and World Bank data. Designed for CHROs to normalize compensation across regions with accurate inflation adjustments. Inputs include country codes, base salary, and reference year. Outputs inflation-adjusted salary with data sources and warnings.

  Paramètres, retour & exemple (5)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • baseSalary · number · requis
  • targetYear · number · optionnel
  • countryCode · string · requis
  • referenceYear · number · requis

  Exemple d'appel

  {"name": "global_salary_inflation_adjuster", "arguments": {"baseSalary": 1, "countryCode": "texte", "referenceYear": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "final", "sources": [], "warnings": [], "targetYear": 1, "countryCode": "texte", "inflationRate": 1, "referenceYear": 1, "adjustedSalary": 1}}

• gov_procurement_multi≈ 1166 tokens

  Aggregate public procurement tenders (calls for tender / appels d'offres) from multiple government sources simultaneously: TED Europa v3 (27 EU countries, keyless API), BOAMP France (opendatasoft, keyless), UK Contracts Finder (OCDS standard, keyless), SAM.gov United States (requires SAM_GOV_API_KEY env var), and bund.de Germany (HTML scraping, partial). Returns structured tender records with buyer authority, EU CPV sector code, estimated contract value converted to EUR via live FX rates, submission deadlines, and direct notice URLs. Use when: a B2G agent needs to find government contract opportunities matching keywords across multiple jurisdictions; building a pipeline of public tenders for bid/no-bid qualification; monitoring a domain by CPV code; market sizing public sector spend. Key inputs: query (keywords), countries (ISO-2 array), cpv_codes (EU standard codes, e.g. 72000000=IT services, 45000000=construction, 79000000=business services), min_value_eur (filter), published_after (ISO date, defaults to 30 days ago). SLA: <=25s p95 (all sources fetched in parallel, 8s budget per source). Optional env var SAM_GOV_API_KEY enables US federal tenders (free key at api.sam.gov). Quality score: 25 pts if TED EU retrieved, 15 pts per other source retrieved (max 60), 10 pts if >= 10 tenders returned, 5 pts if aggregates computed. Status: failed < 30 / partial 30-59 / final >= 60.

  Paramètres, retour & exemple (6)

  Paramètres

  • async · boolean · optionnel
    If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
  • query · string · requis
    Keywords to search for tenders (e.g. "cybersecurity audit", "construction", "consulting AI")
  • countries · array · optionnel
    Countries to search. Defaults to ["EU","US","FR","UK","DE"]. Use "EU" for all 27 EU member states via TED Europa.
  • cpv_codes · array · optionnel
    EU Common Procurement Vocabulary codes (e.g. ['72000000'] for IT services, ['45000000'] for construction). Optional.
  • min_value_eur · number · optionnel
    Minimum contract value in EUR. Tenders below this are excluded. Optional.
  • published_after · string · optionnel
    ISO date YYYY-MM-DD. Only return tenders published after this date. Defaults to 30 days ago.

  Exemple d'appel

  {"name": "gov_procurement_multi", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"query": "texte", "status": "partial", "sources": [], "tenders": [], "by_source": {}, "by_country": {}, "quality_score": 1, "countries_searched": []}}

+ 159 autres outils (affichage limité à 120).

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://mcp.gapup.io