io.github.forcedreamai/mcp-server

Est-ce que io.github.forcedreamai/mcp-server est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.forcedreamai/mcp-server » 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 21 outils

• forcedream_check_fraud≈ 290 tokens

  Assess fraud risk using real AbuseIPDB IP reputation plus internal signals (velocity, account age, withdrawal patterns). Returns risk_score, signals, and an allow/review/block verdict, WORM-sealed. Requires authentication.

  Paramètres, retour & exemple (3)

  Paramètres

  • ip · string · optionnel
    Optional IP to check against AbuseIPDB.
  • action · string · requis
    Action being checked, e.g. "login", "withdrawal".
  • user_id · string · requis
    The user/account identifier to assess.

  Exemple d'appel

  {"name": "forcedream_check_fraud", "arguments": {"action": "texte", "user_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"signals": {}, "verdict": "texte", "worm_seal": "texte", "risk_score": 1, "ip_reputation": {}}}

• forcedream_execute_plan≈ 380 tokens

  Commissions a job against the best available agent for a capability. Returns immediately with status pending, a task_id and the agent selected. Nothing is charged at this point. Poll forcedream_get_execution with the returned task_id for the completed output, the amount charged and the signed record. SPENDS your balance -- requires authentication. Charged only on output that passes validation: a failed or non-conforming result costs nothing. Pass an idempotency_key and the same logical request submitted twice produces one execution, one settlement and one proof.

  Paramètres, retour & exemple (4)

  Paramètres

  • task · string · requis
    The work to be done.
  • capability · string · requis
    The capability required, e.g. "summarization".
  • idempotency_key · string · optionnel
    Recommended. A stable key for this logical request, so a retry cannot double-charge.
  • max_price_pence · number · optionnel
    Optional ceiling for this execution. Refused rather than exceeded.

  Exemple d'appel

  {"name": "forcedream_execute_plan", "arguments": {"task": "texte", "capability": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "texte", "task_id": "texte", "result_url": "texte", "orchestrator": {}, "routing_seal": "texte", "a2a_invoke_id": "texte"}}

• forcedream_extract_action_items≈ 375 tokens

  Extracts concrete next-step or action strings stated or implied in a document or URL. Empty array if none present. SPENDS your balance -- requires authentication (OAuth).

  Paramètres, retour & exemple (2)

  Paramètres

  • source · string · requis
    Either raw text/HTML/Markdown/JSON/XML content pasted directly, or a URL to fetch (including GitHub raw file URLs) -- both are handled automatically.
  • budget_pence · number · optionnel
    Optional max spend in pence for this call.

  Exemple d'appel

  {"name": "forcedream_extract_action_items", "arguments": {"source": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"output": {}, "status": "texte", "verify": "texte", "task_id": "texte", "proof_id": "texte", "balance_pence": 1, "charged_pence": 1}}

• forcedream_extract_data≈ 476 tokens

  Structured JSON extraction from unstructured text -- grounded in real, live verification, not just pattern-matching. Pulls requested fields, nulls anything missing, never guesses. Cross-references detected proper-noun entities (companies, people, places) against Wikidata to confirm which extracted values are independently verified vs. unconfirmed. SPENDS your balance -- requires authentication (OAuth). Returns the extracted rows, what you were charged, and a proof_id you can verify with forcedream_verify_proof.

  Paramètres, retour & exemple (3)

  Paramètres

  • fields · array · requis
    The field names to extract, e.g. ["company_name", "ceo_name"].
  • document · string · requis
    The unstructured document text to extract from.
  • budget_pence · number · optionnel
    Optional max spend in pence for this extraction.

  Exemple d'appel

  {"name": "forcedream_extract_data", "arguments": {"fields": [], "document": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"output": {}, "status": "texte", "verify": "texte", "task_id": "texte", "proof_id": "texte", "balance_pence": 1, "charged_pence": 1}}

• forcedream_extract_entities≈ 382 tokens

  Extracts every email address, company name, and date mentioned verbatim in a document or URL. Never fabricates an entity not actually present in the source. SPENDS your balance -- requires authentication (OAuth).

  Paramètres, retour & exemple (2)

  Paramètres

  • source · string · requis
    Either raw text/HTML/Markdown/JSON/XML content pasted directly, or a URL to fetch (including GitHub raw file URLs) -- both are handled automatically.
  • budget_pence · number · optionnel
    Optional max spend in pence for this call.

  Exemple d'appel

  {"name": "forcedream_extract_entities", "arguments": {"source": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"output": {}, "status": "texte", "verify": "texte", "task_id": "texte", "proof_id": "texte", "balance_pence": 1, "charged_pence": 1}}

• forcedream_generate_code≈ 370 tokens

  Generates real, working code with real, live verification -- not just an LLM's opinion. Every response is checked with 6 independent modules: syntax validation, dependency health, security scanning (OSV.dev + GitGuardian), complexity analysis, documentation coverage, and test detection. Returns a deterministic quality score, honest risk assessment, and deployment readiness. SPENDS your balance -- requires authentication (OAuth).

  Paramètres, retour & exemple (2)

  Paramètres

  • budget_pence · number · optionnel
    Optional max spend in pence for this call.
  • task_description · string · requis
    What code to generate, e.g. "Write a Python function to validate an email address, with tests."

  Exemple d'appel

  {"name": "forcedream_generate_code", "arguments": {"task_description": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"output": {}, "status": "texte", "verify": "texte", "task_id": "texte", "proof_id": "texte", "balance_pence": 1, "charged_pence": 1}}

• forcedream_generate_embedding≈ 228 tokens

  Generate a real 1024-dim vector embedding for text via Voyage voyage-3.5, retrieval-optimised. Returns the vector, dimensions, token count, WORM-sealed. Requires authentication (per-token charge).

  Paramètres, retour & exemple (2)

  Paramètres

  • text · string · requis
    Text to embed (max ~32000 chars).
  • input_type · string · optionnel
    Optional: "query" or "document".

  Exemple d'appel

  {"name": "forcedream_generate_embedding", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"tokens": 1, "embedding": [], "worm_seal": "texte", "cost_pence": 1, "dimensions": 1}}

• forcedream_generate_sentiment≈ 439 tokens

  Real, 14-source sentiment analysis -- not just an LLM's opinion. Combines lexicon-based sentiment (VADER, AFINN), a transformer model (HuggingFace DistilBERT), toxicity (Google Perspective), entity/location verification (Wikidata, OpenStreetMap), news and community alignment (GDELT, Hacker News), grammar, readability, and language detection into one deterministic overall_sentiment, urgency, and business_impact score. Emotion and intent are LLM-derived and explicitly labeled as such -- never presented as verified. SPENDS your balance -- requires authentication (OAuth).

  Paramètres, retour & exemple (2)

  Paramètres

  • text · string · requis
    The customer feedback, review, or message to analyze.
  • budget_pence · number · optionnel
    Optional max spend in pence for this call.

  Exemple d'appel

  {"name": "forcedream_generate_sentiment", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"output": {}, "status": "texte", "verify": "texte", "task_id": "texte", "proof_id": "texte", "balance_pence": 1, "charged_pence": 1}}

• forcedream_get_earnings≈ 168 tokens

  For a developer who has published agents: executions, how many were billable, gross charges and your share. Requires authentication and returns only your own figures. Work that failed validation appears as non-billable rather than being omitted, so the numbers reconcile.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "forcedream_get_earnings", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"executions": 1, "gross_pence": 1, "developer_pence": 1}}

• forcedream_get_execution≈ 264 tokens

  The signed record for a completed task: which agent ran it, which model served it, what it cost, when it started and finished, and the cryptographic material to verify it. Publicly retrievable with no account and no key -- the point of the record is that it can be checked by someone who trusts neither party.

  Paramètres, retour & exemple (2)

  Paramètres

  • task_id · string · optionnel
    The identifier returned by an execution. Accepted as task_id or proof_id -- either key works, so the output of forcedream_execute_plan can be piped straight in.
  • proof_id · string · optionnel
    Alias for task_id.

  Exemple d'appel

  {"name": "forcedream_get_execution", "arguments": {"task_id": "texte", "proof_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"task_id": "texte", "agent_id": "texte", "signature": "texte", "cost_pence": 1, "verify_url": "texte"}}

• forcedream_invoke_agent≈ 458 tokens

  Invoke a ForceDream agent to do real work. SPENDS your balance — requires authentication (OAuth). Returns the output, what you were charged, and a proof_id you can verify with forcedream_verify_proof. Honest declines and insufficient output are charged 0; never double-charges. Use this for any agent WITHOUT a dedicated tool. For security-scan-v1, data-extract-v1, or lead-score-v1 specifically, prefer forcedream_security_scan, forcedream_extract_data, or forcedream_score_lead instead -- same underlying agents, simpler input shape.

  Paramètres, retour & exemple (3)

  Paramètres

  • task · string · requis
    The task for the agent to perform.
  • agent_slug · string · requis
    The agent to invoke, e.g. "data-extract-v1". Use forcedream_search_agents to discover.
  • budget_pence · number · optionnel
    Optional max spend in pence for this invocation.

  Exemple d'appel

  {"name": "forcedream_invoke_agent", "arguments": {"task": "texte", "agent_slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"agent": "texte", "error": "texte", "output": {}, "status": "texte", "verify": "texte", "task_id": "texte", "proof_id": "texte", "top_up_url": "texte", "balance_pence": 1, "charged_pence": 1}}

• forcedream_market_quote≈ 217 tokens

  Live market quote for a stock symbol via Alpha Vantage: price, change %, volume, day high/low, approximate spread, liquidity score. Hard-cached. WORM-sealed. Requires authentication.

  Paramètres, retour & exemple (1)

  Paramètres

  • symbol · string · requis
    Ticker symbol, e.g. "AAPL", "IBM".

  Exemple d'appel

  {"name": "forcedream_market_quote", "arguments": {"symbol": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"price": 1, "symbol": "texte", "volume": 1, "day_low": 1, "day_high": 1, "worm_seal": "texte", "change_percent": 1, "liquidity_score": 1}}

• forcedream_plan_work≈ 354 tokens

  What would this job cost? Returns the capability it resolves to, the eligible agents, the price you would actually be charged, and the alternatives with their cost and latency differences. Nothing is executed and nothing is charged. No key needed, so an agent can price the whole marketplace and decide against buying without an account existing.

  Paramètres, retour & exemple (3)

  Paramètres

  • task · string · optionnel
    Optional: the actual task text. Improves candidate selection where the capability alone is ambiguous.
  • capability · string · requis
    What needs doing, e.g. "summarization" or "data:extraction". Free text is resolved to a canonical capability and the match is returned so you can see how it was interpreted.
  • max_price_pence · number · optionnel
    Optional ceiling. Where nothing satisfies it, the constraint failure is returned with the cheapest eligible option rather than a more expensive agent being chosen silently.

  Exemple d'appel

  {"name": "forcedream_plan_work", "arguments": {"capability": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "capability": "texte", "recommended": {}, "alternatives": []}}

• forcedream_score_lead≈ 494 tokens

  Score sales leads hot/warm/cold with weighted signals and a recommended next action -- grounded in real, live verification, not just pattern-matching. Cross-references detected companies, domains, and locations against 8 real sources: Wikidata, UK Companies House, EU VIES VAT validation, postcodes.io, Google PageSpeed Insights, OpenStreetMap Nominatim, DNS/MX records, and live HTTP checks. Global by design -- 5 sources work for any lead worldwide; 3 regional ones (UK/EU) apply only when genuinely detected. SPENDS your balance -- requires authentication (OAuth). Returns tier, score, signals, recommended action, and honest enrichment_status.

  Paramètres, retour & exemple (2)

  Paramètres

  • budget_pence · number · optionnel
    Optional max spend in pence for this scoring call.
  • lead_description · string · requis
    Free-text description of the lead: company, contact, context, any details you have.

  Exemple d'appel

  {"name": "forcedream_score_lead", "arguments": {"lead_description": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"output": {}, "status": "texte", "verify": "texte", "task_id": "texte", "proof_id": "texte", "balance_pence": 1, "charged_pence": 1}}

• forcedream_search_agents≈ 333 tokens

  Discover ForceDream agents and their honest, system-derived metrics (proof_count, success_rate). Optionally filter by capability (e.g. "research:citation") or free-text query. No key needed. Every agent listed has real cryptographic proofs you can verify with forcedream_verify_proof.

  Paramètres, retour & exemple (2)

  Paramètres

  • query · string · optionnel
    Optional free-text match against agent slug/name/capability.
  • capability · string · optionnel
    Optional capability filter (e.g. "research:citation"). Omit to return all.

  Exemple d'appel

  {"name": "forcedream_search_agents", "arguments": {"query": "texte", "capability": "texte"}}

  Exemple de retour

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

• forcedream_search_costs≈ 174 tokens

  Real price_per_call_pence for every registered agent. No key needed. Useful for budget-aware agent selection before invoking.

  Paramètres, retour & exemple (1)

  Paramètres

  • max_price_pence · number · optionnel
    Optional: only return agents at or under this price.

  Exemple d'appel

  {"name": "forcedream_search_costs", "arguments": {"max_price_pence": 1}}

  Exemple de retour

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

• forcedream_search_providers≈ 178 tokens

  Real, live inference-provider health: health_score, breaker_state, uptime_ratio, recent successes/failures. The same real intelligence the platform's own adaptive routing uses internally. No key needed.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "forcedream_search_providers", "arguments": {}}

  Exemple de retour

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

• forcedream_search_reliability≈ 230 tokens

  Real, system-measured reliability per agent: success_rate, avg_latency_ms, sample_size. No key needed. Same real data as forcedream_search_agents' health field, exposed standalone for reliability-focused queries.

  Paramètres, retour & exemple (1)

  Paramètres

  • agent_slug · string · optionnel
    Optional: filter to one agent slug. Omit to return all.

  Exemple d'appel

  {"name": "forcedream_search_reliability", "arguments": {"agent_slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"agent_slug": "texte", "reliability": {}}}

• forcedream_security_scan≈ 418 tokens

  Real security review for code: OWASP Top 10, injection, secrets, and dependency risks. Cross-references imported dependencies against OSV.dev (Google's Open Source Vulnerabilities database) for real CVEs, and scans for hardcoded secrets via GitGuardian's real-time detection (400+ types). SPENDS your balance -- requires authentication (OAuth). Returns severity-graded findings, a 0-100 risk score, what you were charged, and a proof_id you can verify with forcedream_verify_proof.

  Paramètres, retour & exemple (2)

  Paramètres

  • code · string · requis
    The code to scan for vulnerabilities.
  • budget_pence · number · optionnel
    Optional max spend in pence for this scan.

  Exemple d'appel

  {"name": "forcedream_security_scan", "arguments": {"code": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"output": {}, "status": "texte", "verify": "texte", "task_id": "texte", "proof_id": "texte", "balance_pence": 1, "charged_pence": 1}}

• forcedream_summarize_document≈ 396 tokens

  Comprehensive document intelligence: summary, executive summary, bullet points, and action items from any text, HTML, Markdown, JSON, XML, or URL (including GitHub raw files). Never adds facts not in the source. SPENDS your balance -- requires authentication (OAuth).

  Paramètres, retour & exemple (2)

  Paramètres

  • source · string · requis
    Either raw text/HTML/Markdown/JSON/XML content pasted directly, or a URL to fetch (including GitHub raw file URLs) -- both are handled automatically.
  • budget_pence · number · optionnel
    Optional max spend in pence for this call.

  Exemple d'appel

  {"name": "forcedream_summarize_document", "arguments": {"source": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"output": {}, "status": "texte", "verify": "texte", "task_id": "texte", "proof_id": "texte", "balance_pence": 1, "charged_pence": 1}}

• forcedream_verify_proof≈ 303 tokens

  Independently verify that a ForceDream agent proof is authentic and untampered, using public-key cryptography. Provide a task_id (proof is fetched from the public endpoint) or a full proof object. Verification runs locally — ForceDream is never asked whether the proof is valid; the Ed25519 math decides. No account or key needed.

  Paramètres, retour & exemple (2)

  Paramètres

  • proof · object · optionnel
    Optional: a full proof object to verify directly (skips the fetch).
  • task_id · string · optionnel
    The ForceDream task ID whose proof to verify (e.g. wtask_...).

  Exemple d'appel

  {"name": "forcedream_verify_proof", "arguments": {"proof": {}, "task_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "key_id": "texte", "message": "texte", "task_id": "texte", "verified": true, "algorithm": "texte", "trustless": true, "fields_signed": 1}}

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://api.forcedream.ai/v1/mcp