tools.growthkit/revenue-intelligence

Est-ce que tools.growthkit/revenue-intelligence est sûr ?

Au dernier audit MCP Hub, le serveur MCP « tools.growthkit/revenue-intelligence » 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 74 outils

• addCampaignLeads≈ 379 tokens

  Add one or more leads to a campaign. Standard fields (company_name, contact_email, etc.) go to typed columns. ANY OTHER FIELD you pass automatically gets stored in the metadata jsonb column — no schema migration needed for new fields. Examples of custom fields: booth_number, source_event, scanned_at, follow_up_priority, notes_from_call. Call getCampaignLeadFields first to discover what custom fields are already used in this campaign.

  Paramètres, retour & exemple (3)

  Paramètres

  • leads · array · requis
    Array of lead objects. Standard fields go to columns; unknown keys go to metadata jsonb. Max 100 per call.
  • source · string · optionnel · manual | apollo | hunter | enrichment | mcp | csv_upload
    Default 'mcp'.
  • campaign_id · string · requis
    ID of the campaign (from listCampaigns).

  Exemple d'appel

  {"name": "addCampaignLeads", "arguments": {"leads": [], "campaign_id": "texte"}}

  Exemple de retour

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

• cancelReminder≈ 90 tokens

  Cancel a pending reminder by ID.

  Paramètres, retour & exemple (1)

  Paramètres

  • reminder_id · string · requis
    ID of the pending reminder to cancel (from listReminders).

  Exemple d'appel

  {"name": "cancelReminder", "arguments": {"reminder_id": "texte"}}

  Exemple de retour

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

• checkNotifications≈ 59 tokens

  Check for unread notifications (direct messages and broadcasts).

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "checkNotifications", "arguments": {}}

  Exemple de retour

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

• clearMemories≈ 112 tokens

  Delete ALL memories. Irreversible. Always ask for explicit confirmation. You MUST provide a change_reason.

  Paramètres, retour & exemple (1)

  Paramètres

  • change_reason · string · requis
    REQUIRED: Why all memories should be cleared. Stored in audit log.

  Exemple d'appel

  {"name": "clearMemories", "arguments": {"change_reason": "texte"}}

  Exemple de retour

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

• countMemories≈ 213 tokens

  Return only counts, not content — use for overview/sizing (e.g. 'how many competitor memories exist?') before deciding whether to list or search. Optionally filter by chapter via metadata_filter.chapter. For a per-chapter breakdown in one call, prefer getChapterOverview.

  Paramètres, retour & exemple (1)

  Paramètres

  • metadata_filter · object · optionnel
    Optional metadata filters. Use chapter to count within a specific chapter.

  Exemple d'appel

  {"name": "countMemories", "arguments": {"metadata_filter": {}}}

  Exemple de retour

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

• createCampaign≈ 661 tokens

  Create a new campaign briefing. Use after collecting the 7 required fields via the campaign-briefing-playbook (search 'campaign-briefing-playbook' in playbook chapter to load the methodology). Sets status='draft'. Returns the created campaign id. NEVER call this without first running the playbook conversation — every campaign needs a complete briefing.

  Paramètres, retour & exemple (15)

  Paramètres

  • name · string · requis
    Short campaign label, 3-200 chars. Include strategic axis (e.g. 'Q2-DACH-Maschinenbau-EU-AI-Act').
  • notes · string · optionnel
    Optional internal notes about the campaign.
  • offer · string · requis
    The concrete CTA, NOT the product name. E.g. 'Free 30-day pilot', not 'Buy GrowthKit'.
  • channels · array · requis
    Outreach channels for this campaign: email | linkedin | event | paid | cold_call | referral | webinar.
  • end_date · string · optionnel
    Optional ISO date YYYY-MM-DD. Null = open-ended.
  • start_date · string · requis
    ISO date YYYY-MM-DD.
  • description · string · optionnel
    Optional free-text summary of the campaign.
  • icp_snapshot · object · requis
    Frozen ICP at creation time. May be a NARROWED variant of the user's global ICP.
  • success_metric · object · requis
    { type: 'replies'|'demos'|'sqls'|'pipeline_eur', target: number }
  • briefing_source · string · optionnel · wizard | upload | manual
    Default 'wizard'.
  • messaging_angle · string · requis
    The hook in the first email/message. The news/trend/insight that earns the read.
  • pain_hypothesis · string · requis
    ONE sentence stating the specific pain this campaign assumes the persona has.
  • persona_snapshot · object · requis
    Frozen target persona for this campaign.
  • product_snapshot · object · optionnel
    Frozen product info at creation time. Schema: { name, description, value_props[], differentiators[], pricing_hint }.
  • source_document_id · string · optionnel
    Optional documents.id if briefing was parsed from upload.

  Exemple d'appel

  {"name": "createCampaign", "arguments": {"name": "texte", "offer": "texte", "channels": [], "start_date": "texte", "icp_snapshot": {}, "success_metric": {}}}

  Exemple de retour

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

• createReminder≈ 280 tokens

  Schedule a reminder. Convert relative times to ISO 8601.

  Paramètres, retour & exemple (7)

  Paramètres

  • title · string · requis
    Short reminder title.
  • repeat · string · optionnel · none | daily | weekly | monthly
    Repeat interval: none | daily | weekly | monthly. Default: none.
  • channel · string · optionnel · email | slack | webhook
    Delivery channel: email | slack | webhook.
  • task_id · string · optionnel
    Optional: link this reminder to a task (task UUID). Linked reminders are auto-cancelled when the task is marked done/dropped.
  • remind_at · string · requis
    When to remind, ISO 8601 (convert relative times first).
  • description · string · optionnel
    Optional reminder details.
  • channel_target · string · optionnel
    Optional channel target, e.g. email address or webhook URL.

  Exemple d'appel

  {"name": "createReminder", "arguments": {"title": "texte", "remind_at": "texte"}}

  Exemple de retour

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

• createTask≈ 403 tokens

  Create a prioritized task. Provide the four ICE inputs (impact, confidence, effort_constraint, effort_nonconstraint); the DB computes ice_score. Show the inputs to the user for confirmation before calling.

  Paramètres, retour & exemple (10)

  Paramètres

  • owner · string · optionnel
    Assignee (free text)
  • steps · array · optionnel
    Optional checklist of sub-steps.
  • title · string · requis
    Short task title.
  • bucket · string · optionnel · now | next | later | follow-up
    Time horizon: now | next | later | follow-up.
  • detail · string · optionnel
    Optional longer description of the task.
  • impact · integer · optionnel
    ICE impact, 1-10 (higher = more impact).
  • confidence · number · optionnel
    ICE confidence, 0-1 (probability the impact materializes).
  • effort_constraint · integer · optionnel
    Effort on the bottleneck lane (see workspace label_constraint)
  • related_memory_id · string · optionnel
    Optional ID of a related memory to link.
  • effort_nonconstraint · integer · optionnel
    Effort on the non-bottleneck lane

  Exemple d'appel

  {"name": "createTask", "arguments": {"title": "texte"}}

  Exemple de retour

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

• crmAddNote≈ 203 tokens

  Add a note to a CRM record — a deal, company, or contact. Provide content (HTML supported) and at least one target id (deal_id, company_id, or contact_id). Use to log call summaries, context, or decisions against the record.

  Paramètres, retour & exemple (4)

  Paramètres

  • content · string · requis
    Note text — supports HTML.
  • deal_id · string · optionnel
    Optional deal ID to attach the note to.
  • company_id · string · optionnel
    Optional company ID to attach the note to.
  • contact_id · string · optionnel
    Optional contact ID to attach the note to.

  Exemple d'appel

  {"name": "crmAddNote", "arguments": {"content": "texte"}}

  Exemple de retour

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

• crmCheckConnection≈ 129 tokens

  Check if CRM is connected and which provider is active.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "crmCheckConnection", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"provider": "texte", "connected": true}}

• crmCreateActivity≈ 288 tokens

  Create a follow-up activity on a CRM record. Provide a subject and set type (call | meeting | task | email | deadline; default task). Optionally link it to a deal, company, or contact and set a due_date (YYYY-MM-DD). Use to schedule next steps after an interaction.

  Paramètres, retour & exemple (7)

  Paramètres

  • note · string · optionnel
    Optional note/body for the activity.
  • type · string · optionnel · call | meeting | task | email | deadline
    Activity type. Default: task.
  • deal_id · string · optionnel
    Optional deal ID to link the activity to.
  • subject · string · requis
    Activity subject.
  • due_date · string · optionnel
    Due date YYYY-MM-DD.
  • company_id · string · optionnel
    Optional company ID to link the activity to.
  • contact_id · string · optionnel
    Optional contact ID to link the activity to.

  Exemple d'appel

  {"name": "crmCreateActivity", "arguments": {"subject": "texte"}}

  Exemple de retour

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

• crmCreateCompany≈ 107 tokens

  Create a new company. ALWAYS search first to avoid duplicates.

  Paramètres, retour & exemple (2)

  Paramètres

  • name · string · requis
    Company name.
  • address · string · optionnel
    Company address.

  Exemple d'appel

  {"name": "crmCreateCompany", "arguments": {"name": "texte"}}

  Exemple de retour

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

• crmCreateContact≈ 146 tokens

  Create a new contact. ALWAYS pass company_id when the company exists.

  Paramètres, retour & exemple (4)

  Paramètres

  • name · string · requis
    Full name.
  • email · string · optionnel
    Email address.
  • phone · string · optionnel
    Phone number.
  • company_id · string · optionnel
    Company ID. REQUIRED when company exists.

  Exemple d'appel

  {"name": "crmCreateContact", "arguments": {"name": "texte"}}

  Exemple de retour

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

• crmCreateDeal≈ 183 tokens

  Create a new deal. Requires title + stage_id. MUST call crmGetPipelines first.

  Paramètres, retour & exemple (6)

  Paramètres

  • title · string · requis
    Deal title.
  • value · number · optionnel
    Deal value.
  • currency · string · optionnel
    Currency code. Default: EUR.
  • stage_id · string · requis
    Stage ID from crmGetPipelines.
  • company_id · string · optionnel
    Company ID.
  • contact_id · string · optionnel
    Contact ID.

  Exemple d'appel

  {"name": "crmCreateDeal", "arguments": {"title": "texte", "stage_id": "texte"}}

  Exemple de retour

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

• crmGetCompany≈ 91 tokens

  Get full company details by ID. Returns name, domain, industry, employees, address, CRM link.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Company ID from CRM.

  Exemple d'appel

  {"name": "crmGetCompany", "arguments": {"id": "texte"}}

  Exemple de retour

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

• crmGetCompanyContacts≈ 94 tokens

  Get all contacts linked to a company, by company ID. Use to find who to reach at a known company.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Company ID.

  Exemple d'appel

  {"name": "crmGetCompanyContacts", "arguments": {"id": "texte"}}

  Exemple de retour

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

• crmGetCompanyDeals≈ 100 tokens

  Get all deals linked to a company, by company ID. Use after crmSearchCompany or crmGetCompany to review that company's pipeline.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Company ID.

  Exemple d'appel

  {"name": "crmGetCompanyDeals", "arguments": {"id": "texte"}}

  Exemple de retour

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

• crmGetContact≈ 73 tokens

  Get full contact details by ID.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Contact ID.

  Exemple d'appel

  {"name": "crmGetContact", "arguments": {"id": "texte"}}

  Exemple de retour

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

• crmGetDeal≈ 93 tokens

  Get the full record for one deal by ID. Use after a search or list returns a deal id when you need its complete details.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Deal ID.

  Exemple d'appel

  {"name": "crmGetDeal", "arguments": {"id": "texte"}}

  Exemple de retour

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

• crmGetPipelines≈ 70 tokens

  Get all pipelines with stages. ALWAYS call before creating deals to get valid stage_id.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "crmGetPipelines", "arguments": {}}

  Exemple de retour

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

• crmListCompanies≈ 439 tokens

  List companies from CRM with structured filters. Use for segment queries like 'all pharma companies with 50-200 employees in DACH'. All filter fields optional. Returns companies with id, name, industry, employees, country, and pagination info. Unlike crmSearchCompany (which does fuzzy name search), this does precise structured filtering.

  Paramètres, retour & exemple (1)

  Paramètres

  • filter · object · optionnel
    Filter object. All fields optional.

  Exemple d'appel

  {"name": "crmListCompanies", "arguments": {"filter": {}}}

  Exemple de retour

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

• crmListPeople≈ 366 tokens

  List people/contacts from CRM with structured filters. Use for segment queries like 'all CEOs in pipeline companies'. All filter fields optional. Unlike crmSearchContact (fuzzy lookup of one person by name), this does precise structured filtering across the contact base. Returns contacts with id, name, title, company, and pagination info.

  Paramètres, retour & exemple (1)

  Paramètres

  • filter · object · optionnel
    Filter object. All fields optional.

  Exemple d'appel

  {"name": "crmListPeople", "arguments": {"filter": {}}}

  Exemple de retour

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

• crmSearchCompany≈ 114 tokens

  Search CRM for a company by name. ALWAYS search before creating to avoid duplicates.

  Paramètres, retour & exemple (2)

  Paramètres

  • term · string · requis
    Company name or keyword to search for.
  • limit · integer · optionnel
    Max results. Default: 10.

  Exemple d'appel

  {"name": "crmSearchCompany", "arguments": {"term": "texte"}}

  Exemple de retour

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

• crmSearchContact≈ 150 tokens

  Search CRM for a contact by name or keyword (fuzzy match); returns the top matches. Use to look up one known person. For structured segment queries across the contact base (e.g. 'all CEOs in pipeline companies'), use crmListPeople instead.

  Paramètres, retour & exemple (2)

  Paramètres

  • term · string · requis
    Contact name or keyword.
  • limit · integer · optionnel
    Max results. Default: 10.

  Exemple d'appel

  {"name": "crmSearchContact", "arguments": {"term": "texte"}}

  Exemple de retour

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

• crmUpdateDeal≈ 172 tokens

  Update a deal. Use generic names: company_id, contact_id, expected_close.

  Paramètres, retour & exemple (5)

  Paramètres

  • id · string · requis
    Deal ID.
  • title · string · optionnel
    Optional new deal title.
  • value · number · optionnel
    Optional new deal value.
  • stage_id · string · optionnel
    Optional new stage ID (from crmGetPipelines).
  • expected_close · string · optionnel
    Expected close date YYYY-MM-DD.

  Exemple d'appel

  {"name": "crmUpdateDeal", "arguments": {"id": "texte"}}

  Exemple de retour

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

• deleteDocument≈ 105 tokens

  Delete a document and its associated insights. Irreversible — always confirm with the user first.

  Paramètres, retour & exemple (1)

  Paramètres

  • document_id · string · requis
    ID of the document to delete (from listDocuments).

  Exemple d'appel

  {"name": "deleteDocument", "arguments": {"document_id": "texte"}}

  Exemple de retour

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

• deleteLeadSignal≈ 228 tokens

  Permanently delete ONE why-now signal, e.g. one recorded on the wrong company. Always confirm with the user first: name the company, the signal sentence and its source, and wait for an explicit yes. There is no undo and no version history. signal_id is the `id` of a signal from listLeadSignals (active_only=false also lists expired ones). Only this signal is removed — the lead's other signals stay untouched. If the signal is right and only a detail is wrong, use updateLeadSignal instead. 404 signal_not_found means the id is unknown or not in this workspace.

  Paramètres, retour & exemple (1)

  Paramètres

  • signal_id · string · requis
    UUID of the signal — the `id` field of a signal in listLeadSignals.

  Exemple d'appel

  {"name": "deleteLeadSignal", "arguments": {"signal_id": "texte"}}

  Exemple de retour

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

• deleteMemories≈ 189 tokens

  Delete memories by IDs. Always confirm with user first. You MUST provide a change_reason explaining WHY these memories should be deleted. The reason is stored in the version history audit log.

  Paramètres, retour & exemple (2)

  Paramètres

  • change_reason · string · requis
    REQUIRED: Why these memories are being deleted, e.g. 'Outdated', 'Duplicate', 'User requested cleanup'. Stored in audit log.
  • embedding_ids · array · requis
    IDs of the memories to delete (from searchMemory/listMemories).

  Exemple d'appel

  {"name": "deleteMemories", "arguments": {"change_reason": "texte", "embedding_ids": []}}

  Exemple de retour

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

• discoverSimilar≈ 750 tokens

  Find lookalike companies for a seed and re-rank them by fit. mode='account' (seed={domain}) finds companies similar to that domain via Hunter similar_to; mode='icp' (no seed) discovers companies matching your saved ICP; mode='won_deals' is not yet implemented. Each candidate comes back with similarity_to_seed (0–100 firmographic closeness to the seed), canonical_icp_score (0–100 vs your global ICP; null if not on the Pro plan), divergence + divergence_flag (≥25 = seed diverges from ICP — a product signal), classification, and already_in_crm. Read-only — it never writes and never reveals emails/phones (do that per-lead separately). To control cost, only the top `shortlist_size` pre-ranked candidates are fully enriched + scored; the rest come back with enriched:false and null scores (candidates with enriched:false were NOT evaluated — null is 'not scored', not a low score). NOTE: mode='account' uses Hunter `similar_to`, which requires a Hunter Premium/Data-Platform key; without it, discovery automatically falls back to query/industry filters and says so in `warnings`.

  Paramètres, retour & exemple (6)

  Paramètres

  • mode · string · optionnel · account | icp | won_deals
    account = similar to a seed domain (default); icp = match your saved ICP; won_deals = not yet implemented (returns not_implemented).
  • seed · object · optionnel
    Seed for mode='account', e.g. { domain: 'intertours.de' }. Leave empty for icp/won_deals.
  • limit · integer · optionnel
    Max candidates to return (hard-capped at 25). Default 25.
  • score · boolean · optionnel
    Re-rank with canonical ICP scoring (calculate-alignment). Default true. similarity_to_seed is always returned regardless of this flag.
  • filters · object · optionnel
    Optional Hunter Discover filter overrides, passed straight through. Use Hunter's exact sub-shapes — a wrong shape is silently dropped (or 400s). headquarters_location: { include:[{ country:'DE' }], exclude:[...] } — country is ISO-3166 alpha-2; continent / business_region / state / city are also supported inside those objects (NOT { countries:[...] }). keywords: { include:[...], exclude:[...], match:'any'|'all' } (NOT a flat array — flat → HTTP 400 invalid_keywords). industry: { include:[...], exclude:[...] }. headcount: array of enum buckets ('1-10','11-50','51-200','201-500','501-1000','1001-5000','5001-10000','10001+').
  • shortlist_size · integer · optionnel
    How many top pre-ranked candidates get fully enriched + scored (default 10). Pre-ranking uses the free discover fields (geo, size, emails_count). Lower = cheaper (fewer enrichment credits); the rest are returned unevaluated (enriched:false, null scores).

  Exemple d'appel

  {"name": "discoverSimilar", "arguments": {"mode": "account", "seed": {}, "limit": 1, "score": true, "filters": {}, "shortlist_size": 1}}

  Exemple de retour

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

• email_compose≈ 583 tokens

  Compose an email via the user's connected email provider (currently Gmail; Microsoft 365 coming in Phase B). DEFAULT mode is 'draft' — creates a real draft in Gmail that the user can review before sending. Only use mode='send' when the user explicitly confirms sending with keywords like 'sende', 'schick raus', 'verschicken', 'send it', 'raus damit'. On 'draft' success, response includes draft_url the user can click to open the draft in Gmail. On 'send' success, response includes a tracking_id (1×1 pixel auto-injected for open-tracking). The From address is resolved server-side (5-level precedence: explicit from > user-token integration > user-token default > account default > account email) — do NOT fabricate a From address. Optional crm_deal_id links the message to a deal for future activity writeback. Requires active email provider OAuth connection.

  Paramètres, retour & exemple (10)

  Paramètres

  • to · string · requis
    Recipient email address.
  • from · string · optionnel
    Optional From address override. Must be an address the user has authorized.
  • mode · string · requis · draft | send
    Default: 'draft'. Use 'send' only on explicit user confirmation.
  • subject · string · requis
    Email subject line.
  • provider · string · optionnel · auto | google | microsoft
    Default: 'auto'. Backend resolves from user's active integration.
  • body_html · string · optionnel
    HTML email body with <p>, <br>, <strong>, <a href> tags as needed. For send mode, an open-tracking pixel is auto-injected.
  • body_text · string · optionnel
    Optional plain-text fallback. If only one of body_html/body_text is provided, the other is auto-generated.
  • thread_id · string · optionnel
    Optional Gmail thread ID for replies in-thread.
  • crm_deal_id · string · optionnel
    Optional CRM deal UUID if this email relates to a specific deal.
  • in_reply_to · string · optionnel
    Optional Message-ID of the message being replied to.

  Exemple d'appel

  {"name": "email_compose", "arguments": {"to": "texte", "mode": "draft", "subject": "texte"}}

  Exemple de retour

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

• embedMemory≈ 483 tokens

  Store knowledge into long-term memory. Supports single items and batch embedding (max 50). IMPORTANT — Chapter System: Every memory MUST be classified into exactly one chapter via metadata.chapter. Available chapters: icp, strategy, campaigns, analytics, brand, competitors, learnings, general, pipeline, signals, playbook. Always analyze the content and pick the most specific chapter. Use general only as a last resort. BEFORE STORING: Search target chapter first to check for duplicates. QUALITY: 50-300 words, specific and factual, one concept per memory. AUTO-TAGGING: Before saving ANY memory, search the playbook chapter for 'tag-taxonomy' to load the current tag taxonomy. Then add 3-7 relevant tags as a comma-separated string in metadata.tags (e.g. metadata: { chapter: 'campaigns', tags: 'saas,series-a,dach,linkedin,demand-gen' }). Pick the most specific tags from the taxonomy. You may add 1-2 free-form tags if needed. For batch embeds, tag each item individually. PLAYBOOK SYSTEM: Available playbooks: icp-workshop, onboarding, campaign-brief, weekly-review, competitor-analysis, content-brief. When the user asks to do any of these tasks, use prompts/get to load the full playbook and follow its steps.

  Paramètres, retour & exemple (3)

  Paramètres

  • items · array · optionnel
    Batch embed: array of {content, metadata}. Max 50. Each MUST include metadata.chapter.
  • content · string · optionnel
    Text content to store (for single embed).
  • metadata · object · optionnel
    REQUIRED: Must include chapter key.

  Exemple d'appel

  {"name": "embedMemory", "arguments": {"items": [], "content": "texte", "metadata": {}}}

  Exemple de retour

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

• enrichCompany≈ 553 tokens

  Get company info by domain or name. Returns industry, employees, revenue, location, technologies. Prefer `domain` — it is unambiguous; a name matches whatever the provider thinks it means. `domain_unresolved` is not a provider failure — no provider was called and no credit was spent. The reply carries `candidates` (up to five domains with titles): offer them to the user, or pass `country` / `industry` as hints and try again.

  Paramètres, retour & exemple (6)

  Paramètres

  • name · string · optionnel
    Company name (if the domain is unknown), e.g. 'Seeburger AG'.
  • domain · string · optionnel
    Company domain e.g. seeburger.de
  • country · string · optionnel
    Optional hint for resolving the domain from the name: country name or ISO code, e.g. 'CH'. Only used when `domain` is absent.
  • industry · string · optionnel
    Optional hint for resolving the domain from the name, e.g. 'ERP software'. Only used when `domain` is absent.
  • company_name · string · optionnel
    DEPRECATED — use `name`. Accepted as an alias for one more release so cached tool lists keep working; if both are given, `name` wins.
  • campaign_lead_id · string · optionnel
    Optional. The `id` of a lead from listCampaignLeads (that is campaign_leads.id). Pass it whenever you enrich a lead that is already in a campaign: the result is then written back onto that lead. Contact fields are only filled where they are empty — a hand-curated e-mail is never overwritten, the rival candidate is kept in enrichment_data — while provider, timestamp and a short raw extract are always recorded, so `enriched_at` afterwards means 'this lead was enriched' instead of being a guess. Without it nothing is stored and you only get the result back, which is the right thing for a company that is not a lead yet. ⚠ This is NOT the `lead_id` from pipelineStatus' top_10 or listLeadSignals: that one names the company row, and the write fails with lead_not_found. The reply carries `enrichment_write` with what happened.

  Exemple d'appel

  {"name": "enrichCompany", "arguments": {"name": "texte", "domain": "texte", "country": "texte", "industry": "texte", "company_name": "texte", "campaign_lead_id": "texte"}}

  Exemple de retour

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

• enrichPerson≈ 342 tokens

  Get person profile from email or LinkedIn URL.

  Paramètres, retour & exemple (4)

  Paramètres

  • email · string · optionnel
    Person's email address.
  • linkedin_url · string · optionnel
    Full LinkedIn profile URL.
  • linkedin_handle · string · optionnel
    LinkedIn handle/slug (without the full URL).
  • campaign_lead_id · string · optionnel
    Optional. The `id` of a lead from listCampaignLeads (that is campaign_leads.id). Pass it whenever you enrich a lead that is already in a campaign: the result is then written back onto that lead. Contact fields are only filled where they are empty — a hand-curated e-mail is never overwritten, the rival candidate is kept in enrichment_data — while provider, timestamp and a short raw extract are always recorded, so `enriched_at` afterwards means 'this lead was enriched' instead of being a guess. Without it nothing is stored and you only get the result back, which is the right thing for a company that is not a lead yet. ⚠ This is NOT the `lead_id` from pipelineStatus' top_10 or listLeadSignals: that one names the company row, and the write fails with lead_not_found. The reply carries `enrichment_write` with what happened.

  Exemple d'appel

  {"name": "enrichPerson", "arguments": {"email": "texte", "linkedin_url": "texte", "linkedin_handle": "texte", "campaign_lead_id": "texte"}}

  Exemple de retour

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

• findContacts≈ 383 tokens

  Find contacts at a company. Filter by seniority or department.

  Paramètres, retour & exemple (6)

  Paramètres

  • limit · integer · optionnel
    Max results. Default: 10.
  • domain · string · optionnel
    Company domain to find contacts at.
  • company · string · optionnel
    Company name (if domain unknown).
  • seniority · string · optionnel
    junior, senior, or executive.
  • department · string · optionnel
    sales, marketing, it, etc.
  • campaign_lead_id · string · optionnel
    Optional. The `id` of a lead from listCampaignLeads (that is campaign_leads.id). Pass it whenever you enrich a lead that is already in a campaign: the result is then written back onto that lead. Contact fields are only filled where they are empty — a hand-curated e-mail is never overwritten, the rival candidate is kept in enrichment_data — while provider, timestamp and a short raw extract are always recorded, so `enriched_at` afterwards means 'this lead was enriched' instead of being a guess. Without it nothing is stored and you only get the result back, which is the right thing for a company that is not a lead yet. ⚠ This is NOT the `lead_id` from pipelineStatus' top_10 or listLeadSignals: that one names the company row, and the write fails with lead_not_found. The reply carries `enrichment_write` with what happened.

  Exemple d'appel

  {"name": "findContacts", "arguments": {"limit": 1, "domain": "texte", "company": "texte", "seniority": "texte", "department": "texte", "campaign_lead_id": "texte"}}

  Exemple de retour

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

• findEmail≈ 380 tokens

  Find one person's email by name + domain.

  Paramètres, retour & exemple (6)

  Paramètres

  • domain · string · optionnel
    Company domain to search the email at.
  • company · string · optionnel
    Company name (if domain unknown).
  • full_name · string · optionnel
    Full name (alternative to first_name + last_name).
  • last_name · string · optionnel
    Person's last name.
  • first_name · string · optionnel
    Person's first name.
  • campaign_lead_id · string · optionnel
    Optional. The `id` of a lead from listCampaignLeads (that is campaign_leads.id). Pass it whenever you enrich a lead that is already in a campaign: the result is then written back onto that lead. Contact fields are only filled where they are empty — a hand-curated e-mail is never overwritten, the rival candidate is kept in enrichment_data — while provider, timestamp and a short raw extract are always recorded, so `enriched_at` afterwards means 'this lead was enriched' instead of being a guess. Without it nothing is stored and you only get the result back, which is the right thing for a company that is not a lead yet. ⚠ This is NOT the `lead_id` from pipelineStatus' top_10 or listLeadSignals: that one names the company row, and the write fails with lead_not_found. The reply carries `enrichment_write` with what happened.

  Exemple d'appel

  {"name": "findEmail", "arguments": {"domain": "texte", "company": "texte", "full_name": "texte", "last_name": "texte", "first_name": "texte", "campaign_lead_id": "texte"}}

  Exemple de retour

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

• getAeoReport≈ 419 tokens

  Read the weekly AEO report history — how this workspace's brand shows up in AI answer engines. Per ISO week (field: period) and domain: visibility, share_of_voice and own_cited (all ratios 0..1, multiply by 100 to display a percentage), avg_position (1 = best; null = never mentioned that week, NOT zero), plus prompts_scored and attempted_but_no_data. Each series point also carries per_engine: one entry per answer engine with engine, prompts_scored, attempted_but_no_data, visibility, share_of_voice and avg_position. In per_engine, visibility/share_of_voice/avg_position are null (not 0) when that engine produced no data, and there is deliberately NO own_cited — that one exists only at the week level. Weeks before 2026-08-29 have their per_engine rebuilt from the stored by-engine metrics, so the per-engine trend has no gap. Returns { domains: { <domain-slug>: { series: [...], latest_card } } }. Omit domain to get every tracked domain. Use when the user asks about AI-search visibility, share of voice in LLM answers, or how often the brand gets cited.

  Paramètres, retour & exemple (2)

  Paramètres

  • weeks · integer · optionnel
    Optional. Number of most recent weeks. Default 12.
  • domain · string · optionnel
    Optional. Domain SLUG, not the bare hostname — dots become hyphens, e.g. 'growthkit-tools' or 'growthkit-consulting'. Omit to return all domains. An unknown slug yields an empty result, not an error.

  Exemple d'appel

  {"name": "getAeoReport", "arguments": {"weeks": 1, "domain": "texte"}}

  Exemple de retour

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

• getCampaign≈ 88 tokens

  Get a single campaign with full briefing details and lead-stage counts.

  Paramètres, retour & exemple (1)

  Paramètres

  • campaign_id · string · requis
    ID of the campaign (from listCampaigns).

  Exemple d'appel

  {"name": "getCampaign", "arguments": {"campaign_id": "texte"}}

  Exemple de retour

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

• getCampaignLead≈ 265 tokens

  One campaign lead with everything stored about it: contact, company, score, lifecycle_stage, metadata and the complete enrichment_data. That is where you answer why a contact was chosen and who else was found: enrichment_data.persona holds the trail (persona_naehe, persona_treffer, gewaehlt, alternativen, getauscht), enrichment_data.kandidaten_liste the people the enrichment found, and metadata.vorheriger_kontakt the contact this one replaced. Read-only, spends no credits. ⚠ campaign_lead_id is the `id` of a row from listCampaignLeads (campaign_leads.id). It is NOT the `lead_id` from pipelineStatus' top_10 or listLeadSignals: that one names the company row and answers lead_not_found — exactly as a lead from another workspace does.

  Paramètres, retour & exemple (1)

  Paramètres

  • campaign_lead_id · string · requis
    The `id` of a row from listCampaignLeads (campaign_leads.id).

  Exemple d'appel

  {"name": "getCampaignLead", "arguments": {"campaign_lead_id": "texte"}}

  Exemple de retour

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

• getCampaignLeadFields≈ 160 tokens

  Discover which fields are actually used in a campaign's leads. Returns standard columns with non-null values PLUS all metadata (custom) keys with usage counts and sample values. ALWAYS call this BEFORE asking the user about lead structure or before adding new custom fields — it tells you what's already established for this list.

  Paramètres, retour & exemple (1)

  Paramètres

  • campaign_id · string · requis
    ID of the campaign (from listCampaigns).

  Exemple d'appel

  {"name": "getCampaignLeadFields", "arguments": {"campaign_id": "texte"}}

  Exemple de retour

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

• getChapterOverview≈ 166 tokens

  Get memory count per chapter. Use as FIRST STEP in new conversations or reviews.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "getChapterOverview", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"total": 1, "chapters": []}}

• getDocument≈ 87 tokens

  Get a specific document with fresh download URL and linked insights.

  Paramètres, retour & exemple (1)

  Paramètres

  • document_id · string · requis
    ID of the document (from listDocuments).

  Exemple d'appel

  {"name": "getDocument", "arguments": {"document_id": "texte"}}

  Exemple de retour

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

• getHistory≈ 100 tokens

  Get the version history of a specific memory. Shows all previous versions with timestamps and who made changes.

  Paramètres, retour & exemple (1)

  Paramètres

  • embedding_id · string · requis
    ID of the memory to get history for.

  Exemple d'appel

  {"name": "getHistory", "arguments": {"embedding_id": "texte"}}

  Exemple de retour

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

• getOpenTasks≈ 343 tokens

  Return the workspace's open/in-progress tasks ranked by ICE (highest priority first) plus the total open count. Call this at the START of any planning, prioritization, or 'what should I work on next' discussion to ground the conversation in current open tasks before advising.

  Paramètres, retour & exemple (1)

  Paramètres

  • limit · integer · optionnel
    Max tasks to return. Default: 20.

  Exemple d'appel

  {"name": "getOpenTasks", "arguments": {"limit": 1}}

  Exemple de retour

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

• getSeoReport≈ 294 tokens

  Read the weekly SEO report history for this workspace's domains: Google Search Console clicks and impressions, average position, AI-referral sessions and content-brief counts — one data point per ISO week, oldest first. Returns { domains: { <domain-slug>: { series: [...], latest_card } } }. IMPORTANT: avg_position is null for a week with no data — null is NOT zero and must never be charted or averaged as zero. Omit domain to get every domain the workspace tracks. Use when the user asks how SEO, organic search or Search Console performance developed over time.

  Paramètres, retour & exemple (2)

  Paramètres

  • weeks · integer · optionnel
    Optional. Number of most recent weeks. Default 12.
  • domain · string · optionnel
    Optional. Domain SLUG, not the bare hostname — dots become hyphens, e.g. 'growthkit-tools' or 'growthkit-consulting'. Omit to return all domains. An unknown slug yields an empty result, not an error.

  Exemple d'appel

  {"name": "getSeoReport", "arguments": {"weeks": 1, "domain": "texte"}}

  Exemple de retour

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

• getTopLeads≈ 463 tokens

  Retrieve the highest-scoring leads from the CRM, ranked by ICP fit. Returns company details, contact (if any), 4-dimension score breakdown, and qualitative reasons like 'Industry X — strong match to ICP'. By default filters out leads with <50% data completeness to avoid false-positives from data-sparse ICP matches (e.g. leads where only the contact's seniority matched but industry/employees/country are unknown). Override via filters.min_completeness if you want incomplete leads too. Requires scoreLeads to have been run at least once. Requires Pro plan. Read-only — does not trigger new scoring. Call scoreLeads first if your CRM has new companies or ICP has changed (check icp_version_hash in the response to detect staleness). The fit gate decides on `score_fit` against `fit_gate_min` (default 60), never on `score`: `score` is the composite that ranks leads INSIDE the gate and is structurally low for cold leads, so comparing it with the threshold is always wrong.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Number of leads to return. Default 10, max 100.
  • filters · object · optionnel
    Optional result filters.
  • min_score · integer · optionnel
    Minimum score 0-100 to include. Default 60.

  Exemple d'appel

  {"name": "getTopLeads", "arguments": {"limit": 1, "filters": {}, "min_score": 1}}

  Exemple de retour

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

• getWorkingMemory≈ 246 tokens

  Retrieve the current state for a (kind, key) in the current session. Returns null if not set. Use this when you need to merge into existing state or verify what's stored. NOTE: Active working memory entries are ALSO automatically injected into the system prompt by Build Messages — you usually don't need to call this manually. Only call when you need a specific record's full state on-demand.

  Paramètres, retour & exemple (3)

  Paramètres

  • key · string · requis
    Logical identifier within the kind (same key used in setWorkingMemory).
  • kind · string · requis · wizard | working_set | pinned_entity
    Which kind of state to retrieve: wizard | working_set | pinned_entity.
  • session_id · string · requis
    The current chat session_id. REQUIRED.

  Exemple d'appel

  {"name": "getWorkingMemory", "arguments": {"key": "texte", "kind": "wizard", "session_id": "texte"}}

  Exemple de retour

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

• listCampaignLeads≈ 541 tokens

  List leads in a campaign, optionally filtered by lifecycle_stage or enrichment_status. Returns up to 100 per call. Compact rows by default — id, company name, domain, score, fit_gate, strong_signals, has_email, has_phone, lifecycle_stage — which is what you need to rank and to decide. The compact rows carry no contact. fields=full adds the contact (contact_name, contact_role, contact_email, contact_phone), enrichment_provider, enriched_at and enrichment_persona: why the enrichment picked this contact — persona_naehe (closeness of the contact's role to the campaign persona, 0 to 1), persona_treffer, gewaehlt, the alternativen it passed over, and getauscht when it replaced a contact who was already there; that previous contact is kept in metadata.vorheriger_kontakt. enrichment_persona is null when the lead was never enriched with a persona. For one lead's complete record — including kandidaten_liste, everyone the enrichment found — call getCampaignLead with the row's id. The fit gate decides on `score_fit` against `fit_gate_min` (default 60), never on `score`: `score` is the composite that ranks leads INSIDE the gate and is structurally low for cold leads, so comparing it with the threshold is always wrong.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · integer · optionnel
    Default 50, max 100.
  • fields · string · optionnel · compact | full
    compact for lists and ranking; full when you need contacts or the enrichment trail across the list. For a single lead prefer getCampaignLead. Default compact.
  • campaign_id · string · requis
    ID of the campaign (from listCampaigns).
  • lifecycle_stage · string · optionnel · imported | enriched | scored | crm_ready | crm_synced | rejected | bounced
    Optional: filter by lifecycle stage.
  • enrichment_status · string · optionnel · pending | enriched | failed | skipped
    Optional: filter by enrichment status.

  Exemple d'appel

  {"name": "listCampaignLeads", "arguments": {"campaign_id": "texte"}}

  Exemple de retour

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

• listCampaigns≈ 135 tokens

  List campaigns for the current user, optionally filtered by status. Returns campaign metadata plus per-stage lead counts.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Default 25, max 100.
  • status · string · optionnel · draft | active | paused | completed | archived
    Optional: filter by status: draft | active | paused | completed | archived.

  Exemple d'appel

  {"name": "listCampaigns", "arguments": {"limit": 1, "status": "draft"}}

  Exemple de retour

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

• listDeleted≈ 83 tokens

  List recently deleted memories that can be restored. Shows content preview and deletion info.

  Paramètres, retour & exemple (1)

  Paramètres

  • limit · integer · optionnel
    Max results. Default: 20.

  Exemple d'appel

  {"name": "listDeleted", "arguments": {"limit": 1}}

  Exemple de retour

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

• listDocuments≈ 142 tokens

  List stored documents with optional filtering by category or chapter.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    Max results. Default: 50.
  • offset · integer · optionnel
    Pagination offset. Default: 0.
  • chapter · string · optionnel
    Optional: filter by associated memory chapter.
  • category · string · optionnel
    Optional: filter by storage category.

  Exemple d'appel

  {"name": "listDocuments", "arguments": {"limit": 1, "offset": 1, "chapter": "texte", "category": "texte"}}

  Exemple de retour

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

• listLeadSignals≈ 474 tokens

  List the stored why-now signals for one lead or for a whole campaign: `id` (the signal_id that updateLeadSignal and deleteLeadSignal take), type (funding, hiring, job_change, leadership, acquisition, expansion, tech_change, regulatory, event, inbound, other), the one-sentence signal, its source URL, the observed date, a confidence, and `cite`. Read-only. When you use a signal in outreach, use `cite` VERBATIM as the source line — it is already formatted for the reader ("ad-hoc-news, 27. August 2026"). Never write "observed", "observed_at" or "as observed on": those are field names from our data model, not words a prospect should read. Never present a signal without its source and date.

  Paramètres, retour & exemple (6)

  Paramètres

  • lang · string · optionnel · de | en
    Language of the `cite` line. Default de.
  • limit · integer · optionnel
    Default 50, max 200.
  • lead_id · string · optionnel
    UUID of the LEAD (leads.id), e.g. from pipelineStatus top_10. Either this, campaign_lead_id or campaign_id. Mixing the two lead UUIDs up is no longer a trap: whichever you pass is resolved to the right entity, and an unknown UUID returns 404 with an explanation instead of an empty list.
  • active_only · boolean · optionnel
    Only signals inside their TTL. Default true — an expired signal is not a reason to call.
  • campaign_id · string · optionnel
    All signals of a campaign (from listCampaigns). Either this or one of the lead UUIDs.
  • campaign_lead_id · string · optionnel
    UUID of the CAMPAIGN MEMBERSHIP (campaign_leads.id) — the id from listCampaignLeads or from the pipelineRun candidate list. Resolves to the same signals as lead_id.

  Exemple d'appel

  {"name": "listLeadSignals", "arguments": {"lang": "de", "limit": 1, "lead_id": "texte", "active_only": true, "campaign_id": "texte", "campaign_lead_id": "texte"}}

  Exemple de retour

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

• listMemories≈ 186 tokens

  List stored memories in stored order with pagination. Unlike searchMemory (semantic relevance ranking), use this to browse, enumerate, or audit a chapter — not to find the most relevant memory for a question. Filter by chapter via metadata_filter.chapter.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Max results. Default: 50.
  • offset · integer · optionnel
    Pagination offset. Default: 0.
  • metadata_filter · object · optionnel
    Optional metadata filters. Use chapter to list within a specific chapter.

  Exemple d'appel

  {"name": "listMemories", "arguments": {"limit": 1, "offset": 1, "metadata_filter": {}}}

  Exemple de retour

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

• listReminders≈ 305 tokens

  List reminders, ordered by remind_at ascending. By default returns only pending reminders; pass status=sent|cancelled|all to widen. Optionally scope to one task via task_id. Returns each reminder's id, title, remind_at, and status.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Max results. Default: 50.
  • status · string · optionnel · pending | sent | cancelled | all
    Filter by status: pending | sent | cancelled | all. Default: pending.
  • task_id · string · optionnel
    Optional: only reminders linked to this task.

  Exemple d'appel

  {"name": "listReminders", "arguments": {"limit": 1, "status": "pending", "task_id": "texte"}}

  Exemple de retour

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

• listTasks≈ 389 tokens

  List tasks in the workspace, ranked by ICE (highest first). Optional filters.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    Max results. Default: 50.
  • owner · string · optionnel
    Optional: filter by assignee.
  • bucket · string · optionnel · now | next | later | follow-up
    Optional: filter by bucket: now | next | later | follow-up.
  • status · string · optionnel · open | in_progress | done | dropped
    Optional: filter by status: open | in_progress | done | dropped.

  Exemple d'appel

  {"name": "listTasks", "arguments": {"limit": 1, "owner": "texte", "bucket": "now", "status": "open"}}

  Exemple de retour

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

• listTeam≈ 70 tokens

  List all team members (token holders) for your account. Shows display names, roles, and identifies which token is yours.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "listTeam", "arguments": {}}

  Exemple de retour

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

• pipelineRun≈ 1287 tokens

  Run ONE stage of the qualification chain for the next N candidates. Stages in order: resolve → score → signals → reveal → rescore; rerank follows reveal and re-judges the contacts that are already there. ALWAYS call with dry_run=true first and show the user the candidate count and estimated_credits; only after explicit confirmation call again with dry_run=false and confirm_credits set to the number you showed. reveal spends 3 credits per lead (13 with with_phone) and resolve spends 1 per lead; score, signals and rescore spend none — so resolve needs confirm_credits too, not just reveal. rerank calls no provider at all: it reads the stored candidate lists, and the only credit it can spend is one per contact it actually swaps (the new address is verified). That number is not knowable before the run, so its estimate is 0 — use rerank instead of a second reveal whenever the contacts are there but the wrong people. A stage with 0 candidates is not an error — it means the previous stage has to run first, and the reply then carries `why_zero` with per-condition `counts` and a finished sentence in `de` and `en`: report that reason, never invent one. `why_zero` is absent whenever there are candidates. Never run this against a demo campaign; it is refused with 403. The response ends with `next`: pending counts per stage (label_de/label_en, why_zero at 0) — base every next-step suggestion on it, never on chat history. The fit gate decides on `score_fit` against `fit_gate_min` (default 60), never on `score`: `score` is the composite that ranks leads INSIDE the gate and is structurally low for cold leads, so comparing it with the threshold is always wrong.

  Paramètres, retour & exemple (10)

  Paramètres

  • lang · string · optionnel · de | en
    Language for the signal sentences written by the `signals` stage. Default de. Other stages ignore it.
  • limit · integer · optionnel
    How many candidates to process. Default 10, max 25.
  • stage · string · requis · resolve | score | signals | reveal | rescore | rerank
    resolve = find domain and firmographics. score = ICP fit. signals = why-now scan. reveal = persona, email and optionally phone (SPENDS CREDITS). rescore = second pass once seniority is known. rerank = re-check the contacts you already have against the persona, from the candidate lists reveal stored (0 credits, 1 per contact it actually swaps). Map user language: Firmendaten vervollstaendigen/ergaenzen/anreichern or complete company data = resolve; bewerten/priorisieren/einordnen or score/rank = score, use rescore if the campaign was scored before; Anlaesse/Signale/Trigger/Why-now suchen or find triggers = signals; Ansprechpartner/Kontakte finden, E-Mail/Telefon ermitteln or find contacts = reveal; Kontakte neu bewerten/Ansprechpartner neu pruefen/passt der Kontakt noch or re-check the contacts = rerank
  • dry_run · boolean · optionnel
    true = report candidates and estimated_credits, change nothing. Always do this first.
  • lead_ids · array · optionnel
    Optional: run only on these leads instead of letting the stage choose. Use it when the user names specific companies, for a first careful run on one lead, or to pick up after an aborted run. These are `leads.id` — the `lead_id` from this tool's own dry-run candidates, from pipelineStatus top_10 or from listLeadSignals. It is NOT the `id` from listCampaignLeads: that is the campaign membership (campaign_leads.id), and passing it is not refused — it simply matches nothing, and 0 candidates reads like 'nothing left to do'. Naming leads only NARROWS: whoever the gate excludes stays excluded. One exception, and it is the point of a second attempt: in the resolve stage a named lead is taken up again even inside the two retry windows.
  • min_score · integer · optionnel
    Fit threshold for signals and reveal. Default 60.
  • with_phone · boolean · optionnel
    reveal only: also reveal a mobile number. Default false. A phone costs 10 credits per lead on top of the 3 for the email.
  • campaign_id · string · requis
    ID of the campaign (from listCampaigns).
  • require_signal · boolean · optionnel
    reveal only: require an active why-now signal. Default true. Setting this to false widens who gets contacted — ask the user before you do it.
  • confirm_credits · integer · optionnel
    Required for a paid stage when dry_run is false — reveal and resolve: the exact estimated_credits from the dry run. A mismatch is refused with 409 and a fresh number — the candidate set changed, so show the user the new figure instead of retrying with the old one. rerank is estimated at 0 and therefore runs without a confirmation, although a swap costs one credit; do the dry run anyway and tell the user how many contacts it would re-judge.

  Exemple d'appel

  {"name": "pipelineRun", "arguments": {"stage": "resolve", "campaign_id": "texte"}}

  Exemple de retour

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

• pipelineStatus≈ 372 tokens

  Show where a campaign's leads stand in the qualification chain. Returns the funnel (how many leads have a domain, firmographics, a score, a signal, an email, a phone), how many candidates each stage currently has, and the top 10 leads by priority. Read-only, spends no credits. Call this FIRST whenever the user asks what to do with a campaign — the pending counts tell you which stage to run next. The gate_column field says which signal column the reveal gate uses; if it reads 'active_signals' the gate is softer than specified and weak signals still count. The reply carries `stages` — one entry per stage with its pending count and `label_de`/`label_en`. Use those labels when you name a stage to the user; the internal ids (resolve, reveal) are not words a user knows. `contacts` counts three states, not two: `passend`, `andere_rolle`, `fehlt` — the middle one is the common case that "has an e-mail" hides, a contact who is there but in the wrong role. The fit gate decides on `score_fit` against `fit_gate_min` (default 60), never on `score`: `score` is the composite that ranks leads INSIDE the gate and is structurally low for cold leads, so comparing it with the threshold is always wrong.

  Paramètres, retour & exemple (1)

  Paramètres

  • campaign_id · string · requis
    ID of the campaign (from listCampaigns).

  Exemple d'appel

  {"name": "pipelineStatus", "arguments": {"campaign_id": "texte"}}

  Exemple de retour

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

• place_call≈ 179 tokens

  APP-PRIVATE: initiates a click-to-call to one lead from the user's own verified caller ID. Not model-callable (hidden via _meta.ui.visibility:["app"]). Invoked only by the lead-call-card iframe when the human clicks ☎ Anrufen. The gk_ session token is taken server-side; the app passes campaign_lead_id only.

  Paramètres, retour & exemple (1)

  Paramètres

  • campaign_lead_id · string · requis
    ID of the campaign lead to call (campaign_lead_id from show_callable_leads' structuredContent).

  Exemple d'appel

  {"name": "place_call", "arguments": {"campaign_lead_id": "texte"}}

  Exemple de retour

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

• restoreVersion≈ 125 tokens

  Restore a memory to a previous version. Works for both existing and deleted memories. Use version_id from getHistory or listDeleted results.

  Paramètres, retour & exemple (1)

  Paramètres

  • version_id · string · requis
    The version ID (restore_id) to restore to. Get this from getHistory or listDeleted.

  Exemple d'appel

  {"name": "restoreVersion", "arguments": {"version_id": "texte"}}

  Exemple de retour

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

• save_call_outcome≈ 314 tokens

  APP-PRIVATE: saves the post-call disposition / note / next action for one call. Not model-callable (hidden via _meta.ui.visibility:["app"]). Invoked only by the lead-call-card iframe after a call. The gk_ session token is taken server-side; the app passes call_log_id (from place_call) plus optional disposition / notes / next_action.

  Paramètres, retour & exemple (4)

  Paramètres

  • notes · string · optionnel
    Optional free-text note about the call.
  • call_log_id · string · requis
    call_log_id returned by place_call in its structuredContent.
  • disposition · string · optionnel · interested | no_need | callback | voicemail | wrong_number | dnc
    Optional call disposition.
  • next_action · object · optionnel
    Optional follow-up reminder (typically for a callback disposition).

  Exemple d'appel

  {"name": "save_call_outcome", "arguments": {"call_log_id": "texte"}}

  Exemple de retour

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

• scoreLeads≈ 555 tokens

  Trigger ICP lead scoring. Two independent modes — choose by WHERE the leads live, they do not overlap. (1) CAMPAIGN MODE — mode='campaign' plus campaign_id: scores the leads of one campaign (campaign_leads). Use this whenever the request is about a campaign, an imported/uploaded lead list, or leads that are not in a CRM. Needs no CRM connection and no Pro plan. Scores are written back onto the campaign's leads; read them via listCampaignLeads (score / completeness per lead). (2) CRM MODE — mode='full' | 'delta' | 'company_ids': scores this user's connected CRM companies. 'full' = every company (slow for >1k), 'delta' = only those new or changed since the last run (recommended for routine updates), 'company_ids' = a specific list. Persists to the lead_scores table; read results via getTopLeads. Requires a connected CRM and a Pro plan (active or trialing). If the user has no CRM or no Pro plan, campaign mode is the only mode that will work. Both modes score on the same 4 dimensions (industry 35%, employees 25%, geo 20%, seniority 20%) with missing-data renormalization and return counts plus a per-user summary. Write-operation — it persists scores.

  Paramètres, retour & exemple (3)

  Paramètres

  • mode · string · requis · campaign | full | delta | company_ids
    Which leads to score. 'campaign' scores the leads of one campaign and REQUIRES campaign_id — no CRM and no Pro plan needed. The other three target the connected CRM and require Pro: 'full' scores all CRM companies (slow for >1k), 'delta' only those updated since the last run or not yet scored (recommended for routine updates), 'company_ids' a specific list (requires company_ids).
  • campaign_id · string · optionnel
    UUID of the campaign whose leads to score. REQUIRED when mode='campaign'; ignored in the CRM modes. Get it from listCampaigns.
  • company_ids · array · optionnel
    CRM company IDs to score. Required and only used when mode='company_ids'. Max 100 recommended per call.

  Exemple d'appel

  {"name": "scoreLeads", "arguments": {"mode": "campaign"}}

  Exemple de retour

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

• searchMemory≈ 259 tokens

  Search long-term memory using semantic similarity. ALWAYS SEARCH BEFORE ANSWERING marketing/strategy questions. Use short, specific keywords as queries. Available chapters: icp, strategy, campaigns, analytics, brand, competitors, learnings, general, pipeline, signals, playbook. TAG FILTERING: Memories are auto-tagged. Use metadata_filter with tags key to filter (e.g. metadata_filter: { chapter: 'campaigns', tags: 'linkedin' }).

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    Max results. Default: 10.
  • query · string · requis
    Search keywords — short and specific.
  • match_threshold · number · optionnel
    Min similarity (0-1). Default: 0.5.
  • metadata_filter · object · optionnel
    Filter by metadata. Use chapter to search within a specific chapter.

  Exemple d'appel

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

  Exemple de retour

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

• sendNotification≈ 194 tokens

  Send a notification to a team member. First use listTeam to find the recipient. For 2-person teams, the recipient is auto-resolved.

  Paramètres, retour & exemple (4)

  Paramètres

  • context · object · optionnel
    Optional context, e.g. {chapter: 'icp'}.
  • message · string · requis
    The notification message to send.
  • broadcast · boolean · optionnel
    If true, sends to ALL team members. Default: false.
  • to_prefix · string · optionnel
    Recipient's token_prefix or display_name from listTeam.

  Exemple d'appel

  {"name": "sendNotification", "arguments": {"message": "texte"}}

  Exemple de retour

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

• setTaskWeights≈ 226 tokens

  Set the workspace effort weights (constraint vs non-constraint lane) and optional display labels. Re-stamps open tasks so their ICE re-ranks.

  Paramètres, retour & exemple (4)

  Paramètres

  • w_constraint · number · requis
    Weight for the constraint (bottleneck) effort lane in the ICE score.
  • w_nonconstraint · number · requis
    Weight for the non-constraint effort lane in the ICE score.
  • label_constraint · string · optionnel
    Optional display label for the constraint lane (e.g. 'Engineering').
  • label_nonconstraint · string · optionnel
    Optional display label for the non-constraint lane (e.g. 'Design').

  Exemple d'appel

  {"name": "setTaskWeights", "arguments": {"w_constraint": 1, "w_nonconstraint": 1}}

  Exemple de retour

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

• setWorkingMemory≈ 491 tokens

  Store structured state for the current chat session. Use this to persist data that must survive history compression — wizard fields, suggestion lists, active entities. Three kinds: 'wizard' (multi-turn field collection), 'working_set' (ephemeral suggestion lists with TTL), 'pinned_entity' (durable context). Call this AFTER the user confirms a value, BEFORE moving to the next step. The state object replaces (not merges) — fetch first if you need to merge.

  Paramètres, retour & exemple (6)

  Paramètres

  • key · string · requis
    Logical identifier within a kind. Examples: 'campaign_briefing', 'lead_candidates', 'active_campaign'. Use snake_case.
  • kind · string · requis · wizard | working_set | pinned_entity
    wizard = multi-turn field collection. working_set = ephemeral suggestion lists with TTL. pinned_entity = durable context across turns.
  • state · object · requis
    The full state object to store. Replaces any previous state for this (kind, key). Schema is free-form but conventions: wizard = { fields, required, collected, current_step }; working_set = { items, context }; pinned_entity = { id, name, summary, ... }.
  • status · string · optionnel · active | completed | abandoned
    Default 'active'. Set to 'completed' when a wizard finishes successfully (triggers completed_at timestamp).
  • ttl_turns · integer · optionnel
    Optional TTL in user-turns. After this many turns, the record auto-expires. NULL/omit = permanent (typical for wizard and pinned_entity). Use 5 for working_set / suggestion lists.
  • session_id · string · requis
    The current chat session_id. REQUIRED. Comes from the conversation context.

  Exemple d'appel

  {"name": "setWorkingMemory", "arguments": {"key": "texte", "kind": "wizard", "state": {}, "session_id": "texte"}}

  Exemple de retour

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

• show_callable_leads≈ 304 tokens

  Render an interactive call card of leads that have a phone number, each with a ☎ Anrufen button. The HUMAN user clicks a button to place a click-to-call from their own verified caller ID. This tool ONLY displays the card — it never places a call itself, and there is no model-callable call tool (UWG § 7: calls are human-initiated only). Optionally scope to one campaign_id; omit it to aggregate all callable leads across the user's campaigns. Use when the user asks to see or call leads (e.g. "zeig mir anrufbare Leads", "welche Leads kann ich anrufen"). The fit gate decides on `score_fit` against `fit_gate_min` (default 60), never on `score`: `score` is the composite that ranks leads INSIDE the gate and is structurally low for cold leads, so comparing it with the threshold is always wrong.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Max leads to render. Default 50, max 100.
  • campaign_id · string · optionnel
    Optional campaign UUID (from listCampaigns). Omit to aggregate callable leads across all campaigns.

  Exemple d'appel

  {"name": "show_callable_leads", "arguments": {"limit": 1, "campaign_id": "texte"}}

  Exemple de retour

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

• toggleStep≈ 188 tokens

  Check off or re-open a single step in a task's checklist. Provide the task `id` and the `step_id` of the step to toggle. Omit `done` to flip the step's current state; set done=true/false to force a specific state (idempotent). Use when the user completes or reopens a checklist item on a task that has steps.

  Paramètres, retour & exemple (3)

  Paramètres

  • id · string · requis
    Task UUID.
  • done · boolean · optionnel
    Omit to flip the current state.
  • step_id · string · requis
    ID of the step to toggle (from the task's steps).

  Exemple d'appel

  {"name": "toggleStep", "arguments": {"id": "texte", "step_id": "texte"}}

  Exemple de retour

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

• updateCampaign≈ 1204 tokens

  Update fields on an existing campaign. Pass only the fields to change. Use `scoring` to give THIS campaign its own lead-scoring profile — without it the campaign is scored against the user's global ICP, which is wrong whenever the campaign targets a different market. A campaign with its own profile also re-scores automatically when the profile changes.

  Paramètres, retour & exemple (16)

  Paramètres

  • name · string · optionnel
    Short campaign label, 3-200 chars.
  • notes · string · optionnel
    Optional internal notes about the campaign.
  • offer · string · optionnel
    The concrete CTA, NOT the product name. E.g. 'Free 30-day pilot'.
  • status · string · optionnel · draft | active | paused | completed | archived
    Campaign status: draft | active | paused | completed | archived.
  • scoring · object|null · optionnel
    Lead-scoring profile for THIS campaign, merged into icp_snapshot.scoring (the rest of icp_snapshot is left alone). Fill it only from what the user told you — never from general knowledge or another campaign; a wrong profile scores every lead wrongly and the numbers look plausible either way. Set employees.gate=false when company size is context rather than a criterion ('no hard cut-off', 'roughly', 'kein Gate'): the dimension then counts neither toward the score nor toward completeness. Pass null to remove the profile and fall back to the global ICP. Rejected with scoring_invalid if it names none of industries/employees/geo/seniority.roles.
  • channels · array · optionnel
    Outreach channels for this campaign.
  • end_date · string · optionnel
    Optional ISO date YYYY-MM-DD. Null = open-ended.
  • start_date · string · optionnel
    ISO date YYYY-MM-DD.
  • campaign_id · string · requis
    ID of the campaign to update (from listCampaigns).
  • icp_snapshot · object · optionnel
    Frozen ICP for this campaign. May be a narrowed variant of the global ICP.
  • success_metric · object · optionnel
    { type: 'replies'|'demos'|'sqls'|'pipeline_eur', target: number }
  • messaging_angle · string · optionnel
    The hook in the first email/message — the news/trend/insight that earns the read.
  • pain_hypothesis · string · optionnel
    ONE sentence stating the specific pain this campaign assumes the persona has.
  • persona_snapshot · object · optionnel
    Frozen target persona for this campaign.
  • product_snapshot · object · optionnel
    Frozen product info. Schema: { name, description, value_props[], differentiators[], pricing_hint }.
  • fit_gate_min_score · integer|null · optionnel
    Fit-gate threshold on score_fit for THIS campaign, 0 to 100. Default is 60 when unset — only change it when the user asks. Lower it when a documented signal decides suitability rather than the score: reveal then stops dropping leads that sit just below the default, which is the case this exists for. Pass null to put the campaign back on the default.

  Exemple d'appel

  {"name": "updateCampaign", "arguments": {"campaign_id": "texte"}}

  Exemple de retour

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

• updateCampaignLead≈ 488 tokens

  Update fields on an existing campaign lead. Pass lead_id (UUID from listCampaignLeads) and an updates object with only the fields to change. Use this to mark leads as rejected, manually correct enrichment data, or attach custom metadata. Setting lifecycle_stage='rejected' REQUIRES rejected_reason in the same call. The metadata field is shallow-merged into existing metadata jsonb — existing keys are preserved unless overwritten by the same key. Score/dim_*/icp_version_hash are NOT writable here (those come from scoreLeads). crm_external_id/crm_synced_at are NOT writable either (CRM-Sync owns those).

  Paramètres, retour & exemple (2)

  Paramètres

  • lead_id · string · requis
    UUID of the campaign_lead to update
  • updates · object · requis
    Object with fields to change. metadata is shallow-merged.

  Exemple d'appel

  {"name": "updateCampaignLead", "arguments": {"lead_id": "texte", "updates": {}}}

  Exemple de retour

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

• updateLeadSignal≈ 646 tokens

  Correct ONE stored why-now signal in place. signal_id is the `id` of a signal from listLeadSignals — call that with active_only=false to also see expired signals. updates carries only the fields to change: type, signal, source_url, source_label, observed_at, last_confirmed_at. Anything else is ignored and named in `ignored_fields`. The signal stays on its lead: lead_id is not writable, so a signal recorded on the wrong company is removed with deleteLeadSignal, not moved. Changing type, observed_at or last_confirmed_at makes the database recompute expires_at — the reply says so in `expires_at_neu_berechnet`; expires_at itself cannot be set. Setting last_confirmed_at to the date you re-checked the source revives a signal whose expiry has passed — for signals that describe an ongoing state (e.g. tech_change: the system is still in use). Event types (funding, hiring, …) keep counting from observed_at, so for them last_confirmed_at extends nothing; check `signal.expires_at` in the reply. Errors: 404 signal_not_found (unknown id, or not in this workspace), 409 duplicate_source_url (this lead already has another signal with that URL — delete that one first or use a different source), 400 with code signal_too_short, signal_too_long, invalid_type or source_required.

  Paramètres, retour & exemple (2)

  Paramètres

  • updates · object · requis
    Only the fields to change. At least one of them.
  • signal_id · string · requis
    UUID of the signal — the `id` field of a signal in listLeadSignals.

  Exemple d'appel

  {"name": "updateLeadSignal", "arguments": {"updates": {}, "signal_id": "texte"}}

  Exemple de retour

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

• updateMemory≈ 233 tokens

  Update content or metadata of a stored memory. Use to enrich, fix, or reclassify. You MUST provide a change_reason explaining WHAT changed and WHY. The reason is stored in the version history audit log.

  Paramètres, retour & exemple (4)

  Paramètres

  • new_content · string · optionnel
    Updated text content.
  • embedding_id · string · requis
    ID of the memory to update.
  • new_metadata · object · optionnel
    Optional metadata to replace, e.g. chapter or tags.
  • change_reason · string · requis
    REQUIRED: Why this memory is being updated, e.g. 'Added Q2 metrics', 'Fixed company name', 'User requested update'. Stored in audit log.

  Exemple d'appel

  {"name": "updateMemory", "arguments": {"embedding_id": "texte", "change_reason": "texte"}}

  Exemple de retour

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

• updateTask≈ 434 tokens

  Update fields of a task. Partial update; status='done' sets done_at automatically. ice_score recomputes when impact/confidence/effort change.

  Paramètres, retour & exemple (11)

  Paramètres

  • id · string · requis
    ID of the task to update (from listTasks).
  • owner · string · optionnel
    Assignee (free text).
  • steps · array · optionnel
    Replace the task's checklist. Omit to leave unchanged.
  • title · string · optionnel
    Optional new task title.
  • bucket · string · optionnel · now | next | later | follow-up
    Time horizon: now | next | later | follow-up.
  • detail · string · optionnel
    Optional longer description of the task.
  • impact · integer · optionnel
    ICE impact, 1-10 (higher = more impact).
  • status · string · optionnel · open | in_progress | done | dropped
    New status: open | in_progress | done | dropped.
  • confidence · number · optionnel
    ICE confidence, 0-1 (probability the impact materializes).
  • effort_constraint · integer · optionnel
    Effort on the bottleneck lane (see workspace label_constraint).
  • effort_nonconstraint · integer · optionnel
    Effort on the non-bottleneck lane.

  Exemple d'appel

  {"name": "updateTask", "arguments": {"id": "texte"}}

  Exemple de retour

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

• uploadDocument≈ 288 tokens

  Upload a file to GrowthKit document storage. Optionally extracts text and embeds insights.

  Paramètres, retour & exemple (8)

  Paramètres

  • title · string · optionnel
    Optional document title. Defaults to the filename.
  • chapter · string · optionnel
    Optional memory chapter to associate extracted insights with.
  • category · string · optionnel · battlecards | reports | uploads | exports | templates | presentations
    Optional storage category.
  • filename · string · requis
    Filename with extension.
  • mime_type · string · requis
    MIME type.
  • description · string · optionnel
    Optional short description of the document.
  • file_base64 · string · requis
    Base64-encoded file content.
  • extract_insights · boolean · optionnel
    If true, extract text and embed insights into memory. Default: false.

  Exemple d'appel

  {"name": "uploadDocument", "arguments": {"filename": "texte", "mime_type": "texte", "file_base64": "texte"}}

  Exemple de retour

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

• verifyEmail≈ 87 tokens

  Check if an email is deliverable. Use before outreach.

  Paramètres, retour & exemple (1)

  Paramètres

  • email · string · requis
    Email address to verify for deliverability.

  Exemple d'appel

  {"name": "verifyEmail", "arguments": {"email": "texte"}}

  Exemple de retour

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

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.growthkit.tools