io.github.Trupe-Rs/expert-brain

Est-ce que io.github.Trupe-Rs/expert-brain est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.Trupe-Rs/expert-brain » 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

• ai_receptionist_callback_packet≈ 211 tokens

  Return a human-review callback packet for one AI Receptionist call. The packet is review-only and does not send SMS, place calls, or reply to customers autonomously.

  Paramètres, retour & exemple (2)

  Paramètres

  • call_id · string · requis
  • tenant_id · string · optionnel

  Exemple d'appel

  {"name": "ai_receptionist_callback_packet", "arguments": {"call_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "public_name": "texte", "live_line_touched": true, "no_autonomous_outbound": true}}

• ai_receptionist_review_queue≈ 213 tokens

  List recent AI Receptionist call-loop receipts for human review, including callback and A2P-gated inbound SMS status where present. Returns masked/audit-safe identifiers only.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
  • tenant_id · string · optionnel

  Exemple d'appel

  {"name": "ai_receptionist_review_queue", "arguments": {"limit": 1, "tenant_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "public_name": "texte", "live_line_touched": true, "no_autonomous_outbound": true}}

• ai_receptionist_status≈ 206 tokens

  Read the Desk ticket, CRM callback task, call-link receipt, and A2P-gated inbound SMS posture for one AI Receptionist call ID. Returns masked/status metadata only.

  Paramètres, retour & exemple (2)

  Paramètres

  • call_id · string · requis
  • tenant_id · string · optionnel

  Exemple d'appel

  {"name": "ai_receptionist_status", "arguments": {"call_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "public_name": "texte", "live_line_touched": true, "no_autonomous_outbound": true}}

• artifact_audit≈ 158 tokens

  Read provenance, analyzer findings, gate status, approval state, usage, and export receipts for one tenant-scoped artifact.

  Paramètres, retour & exemple (3)

  Paramètres

  • draft_id · string · optionnel
  • tenant_id · string · requis
  • artifact_id · string · optionnel

  Exemple d'appel

  {"name": "artifact_audit", "arguments": {"tenant_id": "texte"}}

  Exemple de retour

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

• artifact_export≈ 264 tokens

  Create an audited export receipt for an approved artifact or internal draft. External publish remains separate and human-approved.

  Paramètres, retour & exemple (8)

  Paramètres

  • format · string · optionnel · short | long | bullets | paste_safe | markdown | html | email_safe | json
  • target · string · requis · markdown | html | email_draft | linkedin_draft | cogentcast_content | talent_scout_workspace | json | pdf
  • draft_id · string · optionnel
  • tenant_id · string · requis
  • artifact_id · string · optionnel
  • target_config · object · optionnel
  • idempotency_key · string · optionnel
  • approval_event_id · string · optionnel

  Exemple d'appel

  {"name": "artifact_export", "arguments": {"target": "markdown", "tenant_id": "texte"}}

  Exemple de retour

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

• artifact_generate≈ 518 tokens

  Generate a governed, tenant-scoped artifact draft with no-fabrication placeholders, analyzer provenance, MASK, brand status, and approval requirements.

  Paramètres, retour & exemple (17)

  Paramètres

  • lane · string · optionnel · external | internal | sales | authority | application | regulated_financial
  • format · string · optionnel · short | long | bullets | paste_safe | markdown | html | email_safe | json
  • locale · string · optionnel
  • audience · string · optionnel
  • tenant_id · string · requis
  • caller_type · string · optionnel · internal_agent | consumer_chat | external_api | mcp_client
  • brand_kit_id · string · optionnel
  • voice_anchor · string · optionnel
  • artifact_type · string · requis · blog | linkedin_post | proposal | upwork_answer | email | bio | cover_letter | case_study
  • budget_policy · object · optionnel
  • variant_count · integer · optionnel
  • source_context · object|string · optionnel
  • idempotency_key · string · optionnel
  • output_language · string · optionnel
  • variant_strategy · string · optionnel
  • voice_profile_id · string · optionnel
  • analysis_findings · array · optionnel

  Exemple d'appel

  {"name": "artifact_generate", "arguments": {"tenant_id": "texte", "artifact_type": "blog"}}

  Exemple de retour

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

• artifact_refine≈ 427 tokens

  Refine an existing artifact draft while preserving tenant boundary, provenance, MASK status, and approval posture.

  Paramètres, retour & exemple (11)

  Paramètres

  • lane · string · optionnel · external | internal | sales | authority | application | regulated_financial
  • format · string · optionnel · short | long | bullets | paste_safe | markdown | html | email_safe | json
  • audience · string · optionnel
  • draft_id · string · optionnel
  • tenant_id · string · requis
  • artifact_type · string · optionnel · blog | linkedin_post | proposal | upwork_answer | email | bio | cover_letter | case_study
  • source_content · string · optionnel
  • source_context · object|string · optionnel
  • idempotency_key · string · optionnel
  • new_source_context · object|string · optionnel
  • refinement_instruction · string · requis

  Exemple d'appel

  {"name": "artifact_refine", "arguments": {"tenant_id": "texte", "refinement_instruction": "texte"}}

  Exemple de retour

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

• artifact_save≈ 200 tokens

  Approve/save an artifact and mark tenant-scoped learning-loop eligibility. Does not publish externally.

  Paramètres, retour & exemple (7)

  Paramètres

  • approved · boolean · optionnel
  • draft_id · string · requis
  • tenant_id · string · requis
  • reuse_tags · array · optionnel
  • learning_scope · string · optionnel
  • idempotency_key · string · optionnel
  • approval_event_id · string · optionnel

  Exemple d'appel

  {"name": "artifact_save", "arguments": {"draft_id": "texte", "tenant_id": "texte"}}

  Exemple de retour

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

• audit_status≈ 143 tokens

  Read AI Stack Audit project state, deliverable refs, credit ledger, and Desk/CRM links.

  Paramètres, retour & exemple (2)

  Paramètres

  • tenant_id · string · optionnel
  • audit_project_id · string · requis

  Exemple d'appel

  {"name": "audit_status", "arguments": {"audit_project_id": "texte"}}

  Exemple de retour

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

• boot_status≈ 543 tokens

  Read-only StackFast connector health/status check. Does not expose secrets.

  Paramètres, retour & exemple (1)

  Paramètres

  • role · string · optionnel
    Optional expected wallet/MCP consumer role. A mismatch fails role readiness closed.

  Exemple d'appel

  {"name": "boot_status", "arguments": {"role": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "auth": {}, "tools": {}, "service": "texte", "generated_at": "texte", "canonical_url": "texte", "role_readiness": {}, "schema_version": "texte", "role_tool_contract": {}}}

• cogentcast_approval_resolve≈ 350 tokens

  Read and validate a server-recorded, human-authenticated approval receipt by id. An LLM cannot create approvals, impersonate Robert, change visibility, or unlock public release. Uses the existing CogentCast production service; it does not bypass Studio, mint Chief Editor/Robert approval, substitute model output for human authority, publish publicly, or expose credentials.

  Paramètres, retour & exemple (2)

  Paramètres

  • package_id · string · requis
  • approval_receipt_id · string · requis

  Exemple d'appel

  {"name": "cogentcast_approval_resolve", "arguments": {"package_id": "texte", "approval_receipt_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "error": "texte", "result": {}, "gateway_receipt": {}}}

• cogentcast_package_create≈ 1652 tokens

  Create one governed Work Sample from a tenant-bound preview reference, preserve the private narration-review create contract, or append a zero-cost audiobook preparation record through CHIEF_EDITOR_REVIEW. No create path can mint a human pass or make a vendor call. Audiobook Production v1 reuses this five-tool surface: content_type=audiobook_production registers exact manuscript/script/SSML plus provenance, pronunciation, visual/companion, and deterministic-build receipts at zero cost; production.status returns the current derivative and Chief Editor/Gemini/ear/paid/publication gates. Paid canary, full generation, and publication are distinct receipt-gated stages. Uses the existing CogentCast production service; it does not bypass Studio, mint Chief Editor/Robert approval, substitute model output for human authority, publish publicly, or expose credentials.

  Paramètres, retour & exemple (6)

  Paramètres

  • input · object · optionnel
    CogentCast Work Sample, private narration review, or zero-cost governed audiobook preparation input. The selected mode is validated by the production service before state or vendor cost is created.
  • source_hashes · object · optionnel
  • preview_digest · string · requis
  • idempotency_key · string · optionnel
    Caller-stable key for this single create operation. Exact replays return the stored result; a different key is rejected.
  • preview_reference · string · optionnel
    Opaque short-lived reference returned by package.preview.
  • content_fingerprint · string · optionnel
    Exact immutable metadata/source fingerprint returned by package.preview.

  Exemple d'appel

  {"name": "cogentcast_package_create", "arguments": {"preview_digest": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "error": "texte", "result": {}, "gateway_receipt": {}}}

• cogentcast_package_preview≈ 1431 tokens

  Validate a Work Sample, content_type=narration_review, or content_type=audiobook_production configuration without creating state or vendor cost. A failed preview returns no creation-authorizing digest or authoritative cost estimate. Audiobook Production v1 reuses this five-tool surface: content_type=audiobook_production registers exact manuscript/script/SSML plus provenance, pronunciation, visual/companion, and deterministic-build receipts at zero cost; production.status returns the current derivative and Chief Editor/Gemini/ear/paid/publication gates. Paid canary, full generation, and publication are distinct receipt-gated stages. Uses the existing CogentCast production service; it does not bypass Studio, mint Chief Editor/Robert approval, substitute model output for human authority, publish publicly, or expose credentials.

  Paramètres, retour & exemple (1)

  Paramètres

  • input · object · requis
    CogentCast Work Sample, private narration review, or zero-cost governed audiobook preparation input. The selected mode is validated by the production service before state or vendor cost is created.

  Exemple d'appel

  {"name": "cogentcast_package_preview", "arguments": {"input": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "error": "texte", "result": {}, "gateway_receipt": {}}}

• cogentcast_production_run≈ 574 tokens

  Request one leased production stage. The zero-cost Gemini reconciliation stage requires exact dispatch, task, job, source, and Chief Editor receipt binding and cannot mint verification. Cost-bearing canary/full-chunk stages require exact prior Chief Editor, Gemini, and human receipts; provider ambiguity blocks paid retry. This tool cannot record human approval or publish. Audiobook Production v1 reuses this five-tool surface: content_type=audiobook_production registers exact manuscript/script/SSML plus provenance, pronunciation, visual/companion, and deterministic-build receipts at zero cost; production.status returns the current derivative and Chief Editor/Gemini/ear/paid/publication gates. Paid canary, full generation, and publication are distinct receipt-gated stages. Uses the existing CogentCast production service; it does not bypass Studio, mint Chief Editor/Robert approval, substitute model output for human authority, publish publicly, or expose credentials.

  Paramètres, retour & exemple (10)

  Paramètres

  • stage · string · requis
  • chunk_id · string · optionnel
  • package_id · string · requis
  • segment_id · string · optionnel
  • dispatch_id · string · optionnel
  • sample_scope · string · optionnel
  • idempotency_key · string · requis
  • manifest_sha256 · string · optionnel
  • verifier_job_id · string · optionnel
  • verification_task_id · string · optionnel

  Exemple d'appel

  {"name": "cogentcast_production_run", "arguments": {"stage": "texte", "package_id": "texte", "idempotency_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "error": "texte", "result": {}, "gateway_receipt": {}}}

• cogentcast_production_status≈ 470 tokens

  Read tenant-scoped Work Sample, narration-review, or audiobook-production state; exact hashes; current-vs-historical derivative projection; and Chief Editor/Gemini/ear/paid/publication gates. Private source bodies and blob locations are not exposed. Audiobook Production v1 reuses this five-tool surface: content_type=audiobook_production registers exact manuscript/script/SSML plus provenance, pronunciation, visual/companion, and deterministic-build receipts at zero cost; production.status returns the current derivative and Chief Editor/Gemini/ear/paid/publication gates. Paid canary, full generation, and publication are distinct receipt-gated stages. Uses the existing CogentCast production service; it does not bypass Studio, mint Chief Editor/Robert approval, substitute model output for human authority, publish publicly, or expose credentials.

  Paramètres, retour & exemple (1)

  Paramètres

  • package_id · string · requis
    ws_, ccnr_, or ccaud_ package identifier.

  Exemple d'appel

  {"name": "cogentcast_production_status", "arguments": {"package_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "error": "texte", "result": {}, "gateway_receipt": {}}}

• credentials_inventory≈ 402 tokens

  Discover wallet-resolved credential service names and accepted aliases without exposing secret values. Use this when an agent is unsure whether a key exists, sees a key-not-found error, or needs the canonical getAgentKey(service) name. Returns service slugs, env/key aliases, categories, and resolver guidance only; never returns raw credentials.

  Paramètres, retour & exemple (1)

  Paramètres

  • query · string · optionnel
    Optional service, provider, env var, or natural-language query such as openai, OPENAI_API_KEY, gmail, Gemini, FireCrawl, or Vercel.

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "count": 1, "usage": {}, "entries": [], "schema_version": "texte", "raw_secret_values_included": true}}

• dealership_check_lead_follow_up≈ 2400 tokens

  Dealership OS checks a tenant-scoped lead against consent, STOP, quiet-hours, pacing, verified-sender, identity, assignment, and manager-exception rules. It returns an eligibility or hold decision, a human action card, and an opaque receipt. The entitled customer modes are evaluate and synthetic_acceptance. It never sends outreach, clears STOP, writes CRM or inventory, reserves inventory, calculates a deal, approves desk/OTD terms, or replaces human authority; governance registration and STOP recording are operator-only modes.

  Paramètres, retour & exemple (6)

  Paramètres

  • mode · string · requis · evaluate | synthetic_acceptance | register_governance | record_stop
  • stop · object · optionnel
  • tenant_id · string · optionnel
  • evaluation · object · optionnel
  • fixture_id · string · optionnel · synthetic_internet_lead_v1
  • governance · object · optionnel

  Exemple d'appel

  {"name": "dealership_check_lead_follow_up", "arguments": {"mode": "evaluate"}}

  Exemple de retour

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

• dealership_sales_floor_brief≈ 580 tokens

  Dealership OS returns a public-safe, tenant-scoped coaching brief for opportunity leak diagnosis, ownership and next actions, daily manager reconciliation, customer connection, customer-first presentation structure, or an opportunity disposition recommendation. It uses the governed T0 public judgment rail and returns findings, an ordered plan, next actions, citations, a human action card, and an opaque receipt. It never sends outreach, writes CRM or inventory, changes opportunity authority, approves desk/OTD terms, performs an assessment, grants a credential, or exposes protected method bodies.

  Paramètres, retour & exemple (9)

  Paramètres

  • mode · string · optionnel · brief | synthetic_acceptance
  • workflow · string · requis · opportunity_leak_diagnosis | opportunity_ownership_and_next_actions | daily_manager_reconciliation_coaching | customer_situation_connection_plan | presentation_structure_plan | opportunity_disposition_recommendation
  • situation · string · optionnel
    Transient operator-described situation. Do not include unnecessary customer identity or protected source material.
  • tenant_id · string · optionnel
    Optional assertion; must match the authenticated tenant.
  • fixture_id · string · optionnel · synthetic_sales_floor_v1
  • role_context · string · optionnel · salesperson | sales_manager | bdc | gm | unspecified
  • schema_version · string · optionnel · stackfast.dealership_sales_advisor.v1
  • idempotency_key · string · optionnel
  • opportunity_ref · string · optionnel
    Optional opaque tenant-scoped opportunity reference. The advisor does not resolve or mutate it.

  Exemple d'appel

  {"name": "dealership_sales_floor_brief", "arguments": {"workflow": "opportunity_leak_diagnosis"}}

  Exemple de retour

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

• estimator_catalog_search≈ 382 tokens

  Operate on tenant-scoped OCE Estimator/Appraiser catalog sources/items, including the StackFast storefront catalog, through the generic estimator_* control-plane contract.

  Paramètres, retour & exemple (13)

  Paramètres

  • line · object · optionnel
  • lines · array · optionnel
  • query · string · optionnel
  • bridge · object · optionnel
  • format · string · optionnel · pdf | word | excel | html | csv | json
  • approval · object · optionnel
  • source_id · string · optionnel
  • tenant_id · string · optionnel
    Tenant boundary, for example repair-remodel-360.
  • adapter_id · string · optionnel · construction.repair_remodel_360 | construction.generic_remodel | field_service.hvac_light_service
    Vertical adapter.
  • document_id · string · optionnel
  • estimate_id · string · optionnel
  • progress_pct · number · optionnel
  • idempotency_key · string · optionnel

  Exemple d'appel

  {"name": "estimator_catalog_search", "arguments": {"line": {}, "lines": [], "query": "texte", "bridge": {}, "format": "pdf", "approval": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "product": "texte", "no_accounting_write": true, "review_required_before_customer_release": true}}

• estimator_catalog_sources≈ 382 tokens

  Operate on tenant-scoped OCE Estimator/Appraiser catalog sources/items, including the StackFast storefront catalog, through the generic estimator_* control-plane contract.

  Paramètres, retour & exemple (13)

  Paramètres

  • line · object · optionnel
  • lines · array · optionnel
  • query · string · optionnel
  • bridge · object · optionnel
  • format · string · optionnel · pdf | word | excel | html | csv | json
  • approval · object · optionnel
  • source_id · string · optionnel
  • tenant_id · string · optionnel
    Tenant boundary, for example repair-remodel-360.
  • adapter_id · string · optionnel · construction.repair_remodel_360 | construction.generic_remodel | field_service.hvac_light_service
    Vertical adapter.
  • document_id · string · optionnel
  • estimate_id · string · optionnel
  • progress_pct · number · optionnel
  • idempotency_key · string · optionnel

  Exemple d'appel

  {"name": "estimator_catalog_sources", "arguments": {"line": {}, "lines": [], "query": "texte", "bridge": {}, "format": "pdf", "approval": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "product": "texte", "no_accounting_write": true, "review_required_before_customer_release": true}}

• estimator_estimate_add_line≈ 369 tokens

  Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.

  Paramètres, retour & exemple (13)

  Paramètres

  • line · object · optionnel
  • lines · array · optionnel
  • query · string · optionnel
  • bridge · object · optionnel
  • format · string · optionnel · pdf | word | excel | html | csv | json
  • approval · object · optionnel
  • source_id · string · optionnel
  • tenant_id · string · optionnel
    Tenant boundary, for example repair-remodel-360.
  • adapter_id · string · optionnel · construction.repair_remodel_360 | construction.generic_remodel | field_service.hvac_light_service
    Vertical adapter.
  • document_id · string · optionnel
  • estimate_id · string · optionnel
  • progress_pct · number · optionnel
  • idempotency_key · string · optionnel

  Exemple d'appel

  {"name": "estimator_estimate_add_line", "arguments": {"line": {}, "lines": [], "query": "texte", "bridge": {}, "format": "pdf", "approval": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "product": "texte", "no_accounting_write": true, "review_required_before_customer_release": true}}

• estimator_estimate_convert_to_bid≈ 372 tokens

  Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.

  Paramètres, retour & exemple (13)

  Paramètres

  • line · object · optionnel
  • lines · array · optionnel
  • query · string · optionnel
  • bridge · object · optionnel
  • format · string · optionnel · pdf | word | excel | html | csv | json
  • approval · object · optionnel
  • source_id · string · optionnel
  • tenant_id · string · optionnel
    Tenant boundary, for example repair-remodel-360.
  • adapter_id · string · optionnel · construction.repair_remodel_360 | construction.generic_remodel | field_service.hvac_light_service
    Vertical adapter.
  • document_id · string · optionnel
  • estimate_id · string · optionnel
  • progress_pct · number · optionnel
  • idempotency_key · string · optionnel

  Exemple d'appel

  {"name": "estimator_estimate_convert_to_bid", "arguments": {"line": {}, "lines": [], "query": "texte", "bridge": {}, "format": "pdf", "approval": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "product": "texte", "no_accounting_write": true, "review_required_before_customer_release": true}}

• estimator_estimate_convert_to_invoice≈ 376 tokens

  Prepare an OCE Estimator/Appraiser document or QBO handoff contract. Review-gated; does not write to accounting systems.

  Paramètres, retour & exemple (13)

  Paramètres

  • line · object · optionnel
  • lines · array · optionnel
  • query · string · optionnel
  • bridge · object · optionnel
  • format · string · optionnel · pdf | word | excel | html | csv | json
  • approval · object · optionnel
  • source_id · string · optionnel
  • tenant_id · string · optionnel
    Tenant boundary, for example repair-remodel-360.
  • adapter_id · string · optionnel · construction.repair_remodel_360 | construction.generic_remodel | field_service.hvac_light_service
    Vertical adapter.
  • document_id · string · optionnel
  • estimate_id · string · optionnel
  • progress_pct · number · optionnel
  • idempotency_key · string · optionnel

  Exemple d'appel

  {"name": "estimator_estimate_convert_to_invoice", "arguments": {"line": {}, "lines": [], "query": "texte", "bridge": {}, "format": "pdf", "approval": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "product": "texte", "no_accounting_write": true, "review_required_before_customer_release": true}}

• estimator_estimate_create_draft≈ 371 tokens

  Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.

  Paramètres, retour & exemple (13)

  Paramètres

  • line · object · optionnel
  • lines · array · optionnel
  • query · string · optionnel
  • bridge · object · optionnel
  • format · string · optionnel · pdf | word | excel | html | csv | json
  • approval · object · optionnel
  • source_id · string · optionnel
  • tenant_id · string · optionnel
    Tenant boundary, for example repair-remodel-360.
  • adapter_id · string · optionnel · construction.repair_remodel_360 | construction.generic_remodel | field_service.hvac_light_service
    Vertical adapter.
  • document_id · string · optionnel
  • estimate_id · string · optionnel
  • progress_pct · number · optionnel
  • idempotency_key · string · optionnel

  Exemple d'appel

  {"name": "estimator_estimate_create_draft", "arguments": {"line": {}, "lines": [], "query": "texte", "bridge": {}, "format": "pdf", "approval": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "product": "texte", "no_accounting_write": true, "review_required_before_customer_release": true}}

• estimator_estimate_export≈ 368 tokens

  Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.

  Paramètres, retour & exemple (13)

  Paramètres

  • line · object · optionnel
  • lines · array · optionnel
  • query · string · optionnel
  • bridge · object · optionnel
  • format · string · optionnel · pdf | word | excel | html | csv | json
  • approval · object · optionnel
  • source_id · string · optionnel
  • tenant_id · string · optionnel
    Tenant boundary, for example repair-remodel-360.
  • adapter_id · string · optionnel · construction.repair_remodel_360 | construction.generic_remodel | field_service.hvac_light_service
    Vertical adapter.
  • document_id · string · optionnel
  • estimate_id · string · optionnel
  • progress_pct · number · optionnel
  • idempotency_key · string · optionnel

  Exemple d'appel

  {"name": "estimator_estimate_export", "arguments": {"line": {}, "lines": [], "query": "texte", "bridge": {}, "format": "pdf", "approval": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "product": "texte", "no_accounting_write": true, "review_required_before_customer_release": true}}

• estimator_estimate_progress_invoice≈ 375 tokens

  Prepare an OCE Estimator/Appraiser document or QBO handoff contract. Review-gated; does not write to accounting systems.

  Paramètres, retour & exemple (13)

  Paramètres

  • line · object · optionnel
  • lines · array · optionnel
  • query · string · optionnel
  • bridge · object · optionnel
  • format · string · optionnel · pdf | word | excel | html | csv | json
  • approval · object · optionnel
  • source_id · string · optionnel
  • tenant_id · string · optionnel
    Tenant boundary, for example repair-remodel-360.
  • adapter_id · string · optionnel · construction.repair_remodel_360 | construction.generic_remodel | field_service.hvac_light_service
    Vertical adapter.
  • document_id · string · optionnel
  • estimate_id · string · optionnel
  • progress_pct · number · optionnel
  • idempotency_key · string · optionnel

  Exemple d'appel

  {"name": "estimator_estimate_progress_invoice", "arguments": {"line": {}, "lines": [], "query": "texte", "bridge": {}, "format": "pdf", "approval": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "product": "texte", "no_accounting_write": true, "review_required_before_customer_release": true}}

• estimator_estimate_update_line≈ 371 tokens

  Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.

  Paramètres, retour & exemple (13)

  Paramètres

  • line · object · optionnel
  • lines · array · optionnel
  • query · string · optionnel
  • bridge · object · optionnel
  • format · string · optionnel · pdf | word | excel | html | csv | json
  • approval · object · optionnel
  • source_id · string · optionnel
  • tenant_id · string · optionnel
    Tenant boundary, for example repair-remodel-360.
  • adapter_id · string · optionnel · construction.repair_remodel_360 | construction.generic_remodel | field_service.hvac_light_service
    Vertical adapter.
  • document_id · string · optionnel
  • estimate_id · string · optionnel
  • progress_pct · number · optionnel
  • idempotency_key · string · optionnel

  Exemple d'appel

  {"name": "estimator_estimate_update_line", "arguments": {"line": {}, "lines": [], "query": "texte", "bridge": {}, "format": "pdf", "approval": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "product": "texte", "no_accounting_write": true, "review_required_before_customer_release": true}}

• estimator_policy_check≈ 367 tokens

  Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.

  Paramètres, retour & exemple (13)

  Paramètres

  • line · object · optionnel
  • lines · array · optionnel
  • query · string · optionnel
  • bridge · object · optionnel
  • format · string · optionnel · pdf | word | excel | html | csv | json
  • approval · object · optionnel
  • source_id · string · optionnel
  • tenant_id · string · optionnel
    Tenant boundary, for example repair-remodel-360.
  • adapter_id · string · optionnel · construction.repair_remodel_360 | construction.generic_remodel | field_service.hvac_light_service
    Vertical adapter.
  • document_id · string · optionnel
  • estimate_id · string · optionnel
  • progress_pct · number · optionnel
  • idempotency_key · string · optionnel

  Exemple d'appel

  {"name": "estimator_policy_check", "arguments": {"line": {}, "lines": [], "query": "texte", "bridge": {}, "format": "pdf", "approval": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "product": "texte", "no_accounting_write": true, "review_required_before_customer_release": true}}

• estimator_receipt_get≈ 366 tokens

  Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.

  Paramètres, retour & exemple (13)

  Paramètres

  • line · object · optionnel
  • lines · array · optionnel
  • query · string · optionnel
  • bridge · object · optionnel
  • format · string · optionnel · pdf | word | excel | html | csv | json
  • approval · object · optionnel
  • source_id · string · optionnel
  • tenant_id · string · optionnel
    Tenant boundary, for example repair-remodel-360.
  • adapter_id · string · optionnel · construction.repair_remodel_360 | construction.generic_remodel | field_service.hvac_light_service
    Vertical adapter.
  • document_id · string · optionnel
  • estimate_id · string · optionnel
  • progress_pct · number · optionnel
  • idempotency_key · string · optionnel

  Exemple d'appel

  {"name": "estimator_receipt_get", "arguments": {"line": {}, "lines": [], "query": "texte", "bridge": {}, "format": "pdf", "approval": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "product": "texte", "no_accounting_write": true, "review_required_before_customer_release": true}}

• fetch≈ 566 tokens

  Fetch a StackFast Brain result or an authorized immutable session artifact by id through the AI6 MCP reader plane. Use the explicit safe shape with id, page, and page_size, for example fetch({ id: "brain:12345", page: 1, page_size: 12000 }) or fetch({ id: "artifact:474", page: 1, page_size: 12000 }); continue with next_page until complete is true.

  Paramètres, retour & exemple (5)

  Paramètres

  • id · string · requis
    Result id returned by the reader plane, for example brain:12345 or an authorized artifact:474. Prefer this over the legacy aid field.
  • aid · string · optionnel
    Legacy compatibility field for direct brain aid. Prefer id plus explicit page and page_size.
  • page · integer · requis
    Required explicit one-based page number. Use 1 for the first page.
  • next_page · integer · optionnel
    Alias for page when following the next_page value returned by a prior fetch call.
  • page_size · integer · requis
    Required explicit maximum characters returned in this page. Use 12000 unless a smaller page is needed.

  Exemple d'appel

  {"name": "fetch", "arguments": {"id": "texte", "page": 1, "page_size": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "ok": true, "url": "texte", "page": 1, "text": "texte", "title": "texte", "message": "texte", "complete": true, "metadata": {}, "page_end": 1, "next_page": 1, "page_size": 1}}

• growthos_business_brain_interview≈ 334 tokens

  Start or append a GrowthOS Business Brain Interview using the existing interview/session model. Outputs remain draft_review_required before automation.

  Paramètres, retour & exemple (11)

  Paramètres

  • action · string · optionnel · template | start | append_answers | generate_artifacts
  • source · string · optionnel
  • answers · array · optionnel
  • company · string · optionnel
  • lead_id · string|number · optionnel
  • tenant_id · string · optionnel
  • session_id · string · optionnel
  • customer_name · string · optionnel
  • customer_email · string · optionnel
  • interview_type · string · optionnel · growthos_scorecard_interview | growthos_business_brain_interview
  • audit_project_id · string · optionnel

  Exemple d'appel

  {"name": "growthos_business_brain_interview", "arguments": {"action": "template", "source": "texte", "answers": [], "company": "texte", "lead_id": 1, "tenant_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "public_name": "texte", "no_autonomous_outbound": true, "review_required_before_send": true}}

• growthos_digital_clone_packet≈ 320 tokens

  Build a draft GrowthOS digital-clone render packet from normalized signals, evidence, runtime tenant voice profile, and PERSPECTIVE capability grounding. No Robert voice defaults and no autonomous outbound.

  Paramètres, retour & exemple (3)

  Paramètres

  • prospect · object · requis
    Local-business prospect evidence to normalize into signals{} + evidence[].
  • tenant_profile · object · optionnel
    Runtime tenant voice and delivery profile. Required before publication; missing profile returns draft_review_required.
  • perspective_context · string · optionnel
    Optional buyer pain or delivery context to ground through stackfast.perspective.translate.

  Exemple d'appel

  {"name": "growthos_digital_clone_packet", "arguments": {"prospect": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "public_name": "texte", "no_autonomous_outbound": true, "review_required_before_send": true}}

• growthos_opportunity_scout_packet≈ 235 tokens

  Build an Opportunity Scout packet for customer, talent, contract, or capital opportunities using the existing gate-first policy layer and no new persistence table.

  Paramètres, retour & exemple (1)

  Paramètres

  • opportunity · object · requis
    Opportunity input. opportunity_type must be one of the registered Opportunity Scout types.

  Exemple d'appel

  {"name": "growthos_opportunity_scout_packet", "arguments": {"opportunity": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "public_name": "texte", "no_autonomous_outbound": true, "review_required_before_send": true}}

• growthos_owner_facing_report≈ 316 tokens

  Render the canonical GrowthOS scorecard into a sendable owner-facing report with web, email-review-ready, PDF-ready outputs, and optional CogentCast site-review receipt composition. No autonomous send.

  Paramètres, retour & exemple (4)

  Paramètres

  • sender · object · optionnel
  • prospect · object · requis
  • cogentcast_site_review · object · optionnel
    Optional CogentCast site-review request or precomputed receipt. GrowthOS consumes this receipt instead of recreating website review logic.
  • include_cogentcast_site_review · boolean · optionnel
    Fetch a CogentCast dry-run site-review receipt for the supplied website_url and compose it into step 3.

  Exemple d'appel

  {"name": "growthos_owner_facing_report", "arguments": {"prospect": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "public_name": "texte", "no_autonomous_outbound": true, "review_required_before_send": true}}

• growthos_revenue_capture_packet≈ 337 tokens

  Return a GrowthOS revenue-capture packet: scorecard, review-gated contact drafts, CogentCast site-review receipt composition, and summary for supplied local-business evidence. GrowthOS consumes CogentCast receipts instead of recreating website-review logic. No autonomous outbound.

  Paramètres, retour & exemple (4)

  Paramètres

  • sender · object · optionnel
  • prospect · object · requis
  • cogentcast_site_review · object · optionnel
    Optional CogentCast site-review request or precomputed receipt. GrowthOS consumes this receipt instead of recreating website review logic.
  • include_cogentcast_site_review · boolean · optionnel
    Fetch a CogentCast dry-run site-review receipt for the supplied website_url and compose it into step 3.

  Exemple d'appel

  {"name": "growthos_revenue_capture_packet", "arguments": {"prospect": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "public_name": "texte", "no_autonomous_outbound": true, "review_required_before_send": true}}

• growthos_scorecard≈ 282 tokens

  Build a private GrowthOS Revenue Capture Scorecard from supplied public business signals. Human buyers start at /growthos/scorecard; MCP execution requires reader entitlement. Returns scorecard findings only; it never sends outreach.

  Paramètres, retour & exemple (3)

  Paramètres

  • sender · object · optionnel
    Optional sender identity with sender_name and geography.
  • prospect · object · optionnel
    Single local-business prospect input.
  • prospects · array · optionnel
    Batch of up to 25 local-business prospect inputs.

  Exemple d'appel

  {"name": "growthos_scorecard", "arguments": {"sender": {}, "prospect": {}, "prospects": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "public_name": "texte", "no_autonomous_outbound": true, "review_required_before_send": true}}

• reply_compose≈ 320 tokens

  Compose a relationship-safe correspondence decision packet with do_not_say, safe_phrasing, channel constraints, manual approval, and a correspondence_response artifact audit trail. It never sends the message.

  Paramètres, retour & exemple (14)

  Paramètres

  • goal · string · optionnel
  • channel · string · requis · email | linkedin_connect | linkedin_message | sms | call_transcript | voicemail | receptionist_follow_up | recruiter_response
  • surface · string · optionnel
  • signature · string · optionnel
  • tenant_id · string · optionnel
  • constraints · object · optionnel
  • crm_context · object · optionnel
  • referred_by · string · optionnel
  • recipient_name · string · optionnel
  • idempotency_key · string · optionnel
  • inbound_message · string · optionnel
  • persist_artifact · boolean · optionnel
  • capability_context · string · optionnel
  • relationship_context · string · optionnel

  Exemple d'appel

  {"name": "reply_compose", "arguments": {"channel": "email"}}

  Exemple de retour

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

• search≈ 204 tokens

  Search StackFast Brain knowledge through the AI6 MCP reader plane; use fetch with a returned result id for full text.

  Paramètres, retour & exemple (1)

  Paramètres

  • query · string · requis
    Natural language search query.

  Exemple d'appel

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

  Exemple de retour

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

• session_file_read≈ 168 tokens

  Return session artifact metadata and persistent URLs. V1 intentionally omits raw artifact contents.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
  • filename · string · optionnel
  • session_id · string · optionnel
  • artifact_id · integer · optionnel

  Exemple d'appel

  {"name": "session_file_read", "arguments": {"limit": 1, "filename": "texte", "session_id": "texte", "artifact_id": 1}}

  Exemple de retour

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

• talent_scout_application_workup≈ 657 tokens

  Build the detailed workup for one Talent Scout queue item: availability status, fit risks, company pain map, Robert proof-point map, resume angle, application strategy, and a full draft-only application packet with resume edits, cover-letter outline, form-paste answer, compensation guidance, LinkedIn/follow-up drafts, founder-objection answers, first-30-days plan, questions to ask, claims/risk validation, manual submission receipt template, interview prep, and learning-loop signals. Draft/review only; no sends or applications.

  Paramètres, retour & exemple (13)

  Paramètres

  • notes · string · optionnel
  • title · string · optionnel
    Role title lookup when queue_item_id is not known.
  • company · string · optionnel
    Company name lookup when queue_item_id is not known.
  • tenant_id · string · optionnel
  • queue_item_id · string · optionnel
    Preferred exact Talent Scout queue item id. If omitted, provide company and title.
  • application_id · string · optionnel
    Optional ATS/portal application or requisition id, such as R110984. Resolves only to an existing Talent Scout queue/history record.
  • requisition_id · string · optionnel
    Alias for application_id when the id is a req/requisition id.
  • canonical_job_id · string · optionnel
    Optional canonical job id lookup. Resolves only to an existing Talent Scout queue/history record.
  • job_description_text · string · optionnel
    Optional full JD pasted by the owner when the stored role is thin or JavaScript-rendered. It hydrates this draft-only workup without returning the raw JD.
  • portal_application_id · string · optionnel
    Alias for application_id when the id came from an external portal.
  • user_supplied_jd_text · string · optionnel
    Alias for job_description_text. Used as owner-supplied JD evidence only for this governed workup.
  • include_follow_up_plan · boolean · optionnel
  • include_interview_prep · boolean · optionnel

  Exemple d'appel

  {"name": "talent_scout_application_workup", "arguments": {"notes": "texte", "title": "texte", "company": "texte", "tenant_id": "texte", "queue_item_id": "texte", "application_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_browser_fill_receipt≈ 328 tokens

  Build or verify a keyboard-event ATS fill plan from a complete form schema. It maps safe stored profile values, reserves eligibility/EEO/files/signature/submit for the human, and requires per-field readback before reporting staged.

  Paramètres, retour & exemple (8)

  Paramètres

  • send · boolean · optionnel
  • apply · boolean · optionnel
  • fields · array · optionnel
  • submit · boolean · optionnel
  • readbacks · object · optionnel
  • tenant_id · string · optionnel
  • profile_values · object · optionnel
  • schema_receipt · object · optionnel

  Exemple d'appel

  {"name": "talent_scout_browser_fill_receipt", "arguments": {"send": true, "apply": true, "fields": [], "submit": true, "readbacks": {}, "tenant_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_business_email_receipt≈ 526 tokens

  Prepare Hunter.io-style business email enrichment receipts for a qualified contact. Uses wallet SSoT status, verifies before recommending, never sends, and requires human approval.

  Paramètres, retour & exemple (14)

  Paramètres

  • email · string · optionnel
    Known business email to confirm from governed mailbox evidence. This path never calls a third-party enrichment provider.
  • domain · string · optionnel
  • last_name · string · optionnel
  • tenant_id · string · optionnel
  • first_name · string · optionnel
  • person_name · string · optionnel
  • sqlite_path · string · optionnel
    Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • company_name · string · optionnel
  • email_source · string · optionnel · governed_mailbox | human_confirmed
    Provenance for a supplied known business email.
  • person_label · string · optionnel
  • auth_token_key · string · optionnel
    Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • database_url_key · string · optionnel
    Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • company_target_id · string · optionnel
  • tenant_database_type · string · optionnel · internal | sovereign_cloud | byoc
    Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.

  Exemple d'appel

  {"name": "talent_scout_business_email_receipt", "arguments": {"email": "texte", "domain": "texte", "last_name": "texte", "tenant_id": "texte", "first_name": "texte", "person_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_compose_application≈ 1013 tokens

  Compose a draft-only first-party job-seeker application artifact for the account owner from a real Talent Scout queue item using JD evidence. Supports cover letter, form paste, application Q&A, telephone script, and authority analysis only; never sends, applies, screens people, ranks people, or makes hiring decisions. This does not screen applicants, rank candidates, or make hiring decisions.

  Paramètres, retour & exemple (22)

  Paramètres

  • notes · string · optionnel
  • title · string · optionnel
    Optional lookup key. Use with company when queue_item_id is not known; exact normalized match is required.
  • company · string · optionnel
    Optional lookup key. Use with title when queue_item_id is not known; exact normalized match is required.
  • actor_id · string · optionnel
  • tenant_id · string · optionnel
  • careers_url · string · optionnel
    Official careers page URL when known. Helps distinguish a real posting from a generic board/root page.
  • output_kind · string · optionnel · cover_letter | form_paste | application_qa | telephone_script | authority_analysis
  • voice_anchor · string · optionnel
  • queue_item_id · string · optionnel
  • application_id · string · optionnel
    Optional ATS/portal application or requisition id, such as R110984. Resolves only to an existing Talent Scout queue/history record.
  • requisition_id · string · optionnel
    Alias for application_id when the id is a req/requisition id.
  • writer_provider · string · optionnel · openai | google_gemini | gemma | bounded_fallback
    Optional writer lane override. Defaults to OpenAI when a wallet key is available; bounded_fallback stays available as a fail-closed safety net.
  • canonical_job_id · string · optionnel
    Optional canonical job id lookup. Resolves only to an existing Talent Scout queue/history record.
  • compare_providers · boolean · optionnel
    When true, run bounded OpenAI/Gemma/Gemini comparison receipts without exposing alternate raw drafts.
  • owner_profile_text · string · optionnel
    Optional private owner evidence from a resume/profile setup interview. Used for proof mapping; never returned raw.
  • baseline_resume_text · string · optionnel
    Optional private owner evidence override. Used only to map JD requirements to proof points; never returned raw.
  • company_homepage_url · string · optionnel
    Official company homepage URL for company-context evidence and human review.
  • company_profile_text · string · optionnel
    Optional official company-site/about/product evidence. Used to target the draft to the company context; never returned raw.
  • job_description_text · string · optionnel
    Manual recovery path only. Paste the full JD when the ATS blocks or JS-renders and Talent Scout returns needs_jd_hydration.
  • linkedin_profile_text · string · optionnel
    Optional manual LinkedIn profile paste/export when LinkedIn blocks automated fetch. Used as owner evidence; never returned raw.
  • portal_application_id · string · optionnel
    Alias for application_id when the id came from an external portal.
  • user_supplied_jd_text · string · optionnel
    Alias for job_description_text; treated as authoritative user-supplied JD evidence after auto-hydration fails.

  Exemple d'appel

  {"name": "talent_scout_compose_application", "arguments": {"notes": "texte", "title": "texte", "company": "texte", "actor_id": "texte", "tenant_id": "texte", "careers_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_correct_relationship_activity≈ 596 tokens

  Append an immutable correction for the channel and direction of an existing Talent Scout Relationship Core receipt. The original receipt is never changed; this tool never sends, applies, scrapes, or changes candidacy status.

  Paramètres, retour & exemple (10)

  Paramètres

  • channel · string · requis · email | linkedin | sms | call | visit
  • direction · string · requis · inbound | outbound | lifecycle
    Explicit corrected message direction; no default is inferred.
  • tenant_id · string · requis
  • sqlite_path · string · optionnel
    Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • auth_token_key · string · optionnel
    Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • idempotency_key · string · requis
    Caller-stable key that makes retries return the original immutable correction receipt.
  • database_url_key · string · optionnel
    Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • correction_reason · string · requis
    Human-attested reason for this append-only correction (maximum 5,000 characters).
  • original_receipt_id · string · requis
    Immutable relationship activity receipt being corrected; it is never rewritten.
  • tenant_database_type · string · optionnel · internal | sovereign_cloud | byoc
    Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.

  Exemple d'appel

  {"name": "talent_scout_correct_relationship_activity", "arguments": {"channel": "email", "direction": "inbound", "tenant_id": "texte", "idempotency_key": "texte", "correction_reason": "texte", "original_receipt_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_create_packet≈ 242 tokens

  Create a draft-only application or opportunity packet from an existing Talent Scout queue item. Human approval is required before external use.

  Paramètres, retour & exemple (6)

  Paramètres

  • notes · string · optionnel
  • actor_id · string · optionnel
  • tenant_id · string · optionnel
  • output_kind · string · optionnel
  • queue_item_id · string · requis
  • opportunity_mode · string · optionnel

  Exemple d'appel

  {"name": "talent_scout_create_packet", "arguments": {"queue_item_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_daily_pipeline≈ 676 tokens

  Return the closed-loop Talent Scout daily operating report from the shared tenant queue: applied pipeline, mailbox reconciliation status, follow-up due, open roles, availability checks, preference filters, stale/closed rows, new discoveries, bounded needs_role_hydration recovery, and a 3-5 role slate. Mailbox reconciliation runs server-side via the StackFast service-account reader. Clients MUST NOT invoke their own Gmail/email connector; if mailbox_reconciliation_status is not ok, surface the red receipt and stop instead of substituting a client-side mailbox read. Read-only control-tower view; no sends or applications.

  Paramètres, retour & exemple (11)

  Paramètres

  • limit · integer · optionnel
  • compact · boolean · optionnel
    Return counts, status buckets, mailbox status, and a bounded slate without full bucket payloads. Defaults true for hosted MCP latency.
  • profile · object · optionnel
    Alias for owner_profile when reviewing stale queue items.
  • tenant_id · string · optionnel
  • slate_limit · integer · optionnel
  • include_items · boolean · optionnel
    Return top-level queue cards. Defaults false so compact daily reads return the bounded operating summary only.
  • owner_profile · object · optionnel
    Optional owner preference context used to refresh stale zero-score queue items inside this tenant only.
  • section_limit · integer · optionnel
  • hydration_limit · integer · optionnel
    Bounded live-hydration attempts for thin roles before compose. Reports attempts and remaining needs_role_hydration; never applies or sends.
  • include_applied · boolean · optionnel
    Include already-applied rows in the applied/waiting pipeline buckets.
  • include_archived · boolean · optionnel
    Include archived, rejected, passed, stale, or already-applied rows. Defaults false for active work queues.

  Exemple d'appel

  {"name": "talent_scout_daily_pipeline", "arguments": {"limit": 1, "compact": true, "profile": {}, "tenant_id": "texte", "slate_limit": 1, "include_items": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_discover_companies_by_campaign≈ 653 tokens

  Preview the account owner's saved business-list campaign. Returns public company websites, employee-count confidence, source receipts, and next actions for manual review. Read-only by default: it does not persist companies unless persist_results is explicitly true and never scrapes LinkedIn.

  Paramètres, retour & exemple (12)

  Paramètres

  • limit · integer · optionnel
  • sources · array · optionnel
  • tenant_id · string · optionnel
  • campaign_id · string · optionnel
  • sqlite_path · string · optionnel
    Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • campaign_name · string · optionnel
  • auth_token_key · string · optionnel
    Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • persist_results · boolean · optionnel
    When true, persist discovered company records to the Talent Scout campaign store. Defaults false so hosted MCP discovery remains a read-only preview for human review.
  • database_url_key · string · optionnel
    Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • allow_live_firecrawl · boolean · optionnel
    Backward-compatible refresh flag; Firecrawl is only a fallback/search or downstream extraction provider, not the Stage 1 radar.
  • tenant_database_type · string · optionnel · internal | sovereign_cloud | byoc
    Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.
  • allow_live_google_places · boolean · optionnel
    Refresh public business website leads through the configured directory provider and distance check. Websites are required before downstream enrichment. Set false only for an explicit no-network dry run.

  Exemple d'appel

  {"name": "talent_scout_discover_companies_by_campaign", "arguments": {"limit": 1, "sources": [], "tenant_id": "texte", "campaign_id": "texte", "sqlite_path": "texte", "campaign_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_discover_local_companies≈ 713 tokens

  Preview the account owner's saved local business-list campaign. Returns public company websites only, with size-band confidence and source receipts for manual review. Read-only by default; set persist_results true only for an intentional store update.

  Paramètres, retour & exemple (18)

  Paramètres

  • limit · integer · optionnel
  • sources · array · optionnel
  • tenant_id · string · optionnel
  • campaign_id · string · optionnel
  • sqlite_path · string · optionnel
    Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • campaign_name · string · optionnel
  • auth_token_key · string · optionnel
    Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • radius_minutes · integer · optionnel
  • persist_results · boolean · optionnel
    When true, persist discovered company records to the Talent Scout campaign store. Defaults false so hosted MCP discovery remains a read-only preview for human review.
  • company_size_max · integer · optionnel
  • company_size_min · integer · optionnel
  • database_url_key · string · optionnel
    Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • geography_anchor · string · optionnel
  • target_role_lanes · array · optionnel
  • allow_live_firecrawl · boolean · optionnel
    Backward-compatible refresh flag; Firecrawl is only a fallback/search or downstream extraction provider, not the Stage 1 radar.
  • target_company_lanes · array · optionnel
  • tenant_database_type · string · optionnel · internal | sovereign_cloud | byoc
    Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.
  • allow_live_google_places · boolean · optionnel
    Refresh public business website leads through the configured directory provider and distance check. Websites are required before downstream enrichment.

  Exemple d'appel

  {"name": "talent_scout_discover_local_companies", "arguments": {"limit": 1, "sources": [], "tenant_id": "texte", "campaign_id": "texte", "sqlite_path": "texte", "campaign_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_draft_manual_note≈ 590 tokens

  Preview a manual note for Robert to copy or edit himself. This read-only tool does not send, store, contact anyone, scrape LinkedIn, enrich private people data, or create a draft record.

  Paramètres, retour & exemple (20)

  Paramètres

  • goal · string · optionnel · applied_follow_up | exploratory_intro | referral_path
  • send · boolean · optionnel
  • apply · boolean · optionnel
  • title · string · optionnel
  • channel · string · optionnel · linkedin | email | sms | phone | in_person
  • company · string · optionnel
  • tenant_id · string · optionnel
  • role_title · string · optionnel
    Exact role title; accepted alongside title for applied follow-up resolution.
  • campaign_id · string · optionnel
  • person_name · string · optionnel
  • sqlite_path · string · optionnel
    Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • company_name · string · optionnel
  • contact_name · string · optionnel
  • person_label · string · optionnel
  • queue_item_id · string · optionnel
  • application_id · string · optionnel
  • auth_token_key · string · optionnel
    Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • database_url_key · string · optionnel
    Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • company_target_id · string · optionnel
  • tenant_database_type · string · optionnel · internal | sovereign_cloud | byoc
    Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.

  Exemple d'appel

  {"name": "talent_scout_draft_manual_note", "arguments": {"goal": "applied_follow_up", "send": true, "apply": true, "title": "texte", "channel": "linkedin", "company": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_draft_outreach≈ 291 tokens

  Draft a human-reviewed manual note from safe pains and voice evidence. The tool never sends messages and fails closed on auto-send/apply requests.

  Paramètres, retour & exemple (8)

  Paramètres

  • send · boolean · optionnel
  • apply · boolean · optionnel
  • pains · array · requis
  • tenant_id · string · optionnel
  • target_name · string · requis
  • artifact_type · string · optionnel
  • voice_profile · string · optionnel
  • voice_samples · array · optionnel

  Exemple d'appel

  {"name": "talent_scout_draft_outreach", "arguments": {"pains": [], "target_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_explain_preferences_match≈ 328 tokens

  Explain in prose how an existing saved job overlaps with and differs from the account owner's stated workplace preferences. Returns preference-language observations only, with no numbers, rankings, recommendations, decisions, or external actions.

  Paramètres, retour & exemple (3)

  Paramètres

  • tenant_id · string · optionnel
  • queue_item_id · string · requis
    Identifier for a job already saved in the account owner's private Talent Scout queue.
  • owner_preferences · object · requis
    The account owner's own stated workplace preferences, such as schedule, location, compensation, travel, responsibilities, and environment.

  Exemple d'appel

  {"name": "talent_scout_explain_preferences_match", "arguments": {"queue_item_id": "texte", "owner_preferences": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_form_schema_receipt≈ 334 tokens

  Enumerate every required and optional ATS form field before any fill attempt. Returns a stable schema hash and complete-field receipt; it never types, uploads, applies, clicks, or submits.

  Paramètres, retour & exemple (5)

  Paramètres

  • send · boolean · optionnel
  • apply · boolean · optionnel
  • fields · array · requis
  • submit · boolean · optionnel
  • tenant_id · string · optionnel

  Exemple d'appel

  {"name": "talent_scout_form_schema_receipt", "arguments": {"fields": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_generate_finished_resume≈ 363 tokens

  Generate a tenant-scoped, draft-only standalone resume from a hydrated role and stored applicant proof bank, export it to PDF through Artifact Studio, and return a render-readback receipt. It never sends, applies, or approves external use.

  Paramètres, retour & exemple (11)

  Paramètres

  • title · string · optionnel
  • company · string · optionnel
  • tenant_id · string · optionnel
  • queue_item_id · string · optionnel
  • application_id · string · optionnel
  • requisition_id · string · optionnel
  • idempotency_key · string · requis
    Stable replay-safe generation/export identity.
  • canonical_job_id · string · optionnel
  • job_description_text · string · optionnel
    Optional private owner-supplied JD evidence for a thin stored role.
  • portal_application_id · string · optionnel
  • user_supplied_jd_text · string · optionnel

  Exemple d'appel

  {"name": "talent_scout_generate_finished_resume", "arguments": {"idempotency_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_import_byoc_delta≈ 356 tokens

  Import a guarded BYOC-local Talent Scout queue delta into the cloud queue. This is closed-world queue bookkeeping only: it never applies, sends, clicks, or submits anything automatically.

  Paramètres, retour & exemple (11)

  Paramètres

  • send · boolean · optionnel
  • apply · boolean · optionnel
  • delta · object · optionnel
  • roles · array · optionnel
  • source · string · optionnel
  • packets · array · optionnel
  • contacts · array · optionnel
  • direction · string · optionnel · byoc_to_cloud
  • tenant_id · string · optionnel
  • idempotency_key · string · optionnel
  • queue_sync_version · string · optionnel

  Exemple d'appel

  {"name": "talent_scout_import_byoc_delta", "arguments": {"send": true, "apply": true, "delta": {}, "roles": [], "source": "texte", "packets": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_mail_signals≈ 267 tokens

  Read Talent Scout mail-signal status from the same server-side Gmail reconciliation path used by review_queue. This is the reliable StackFast replacement for local BYOC scout.mail_signals when the cleverq.net/local tunnel is down: it never calls a client Gmail connector, never returns raw mail bodies, and fails soft with mailbox_reconciliation_status instead of a bare 502.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
  • tenant_id · string · optionnel

  Exemple d'appel

  {"name": "talent_scout_mail_signals", "arguments": {"limit": 1, "tenant_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_my_profile_status≈ 430 tokens

  Read a compact, redacted readiness receipt for the account owner's private Talent Scout profile setup, including profile_version_updated_at for guarded writes through either public profile-upsert alias. Returns only setup status, compose readiness, and active search-rail readiness; never returns raw resume, LinkedIn, work history, claims, or private owner profile text.

  Paramètres, retour & exemple (5)

  Paramètres

  • tenant_id · string · optionnel
  • sqlite_path · string · optionnel
    Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • auth_token_key · string · optionnel
    Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • database_url_key · string · optionnel
    Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • tenant_database_type · string · optionnel · internal | sovereign_cloud | byoc
    Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.

  Exemple d'appel

  {"name": "talent_scout_my_profile_status", "arguments": {"tenant_id": "texte", "sqlite_path": "texte", "auth_token_key": "texte", "database_url_key": "texte", "tenant_database_type": "internal"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_my_profile_upsert≈ 1066 tokens

  Create or update the account owner's private Talent Scout profile setup once so compose, fit, and packet tools can reuse self-entered resume, LinkedIn, proof-point, preference, and voice evidence without re-pasting it for every role. Existing profiles require the current profile_version_updated_at from Talent Scout My Profile Status as if_match_updated_at. Stores private owner evidence for proof mapping and never returns raw resume or LinkedIn text.

  Paramètres, retour & exemple (26)

  Paramètres

  • mode · string · optionnel · merge | replace
  • dry_run · boolean · optionnel
    Preview the redacted owner-profile update without writing stored resume, LinkedIn, proof, or rail evidence. Use this for connector smoke tests.
  • tenant_id · string · optionnel
  • sqlite_path · string · optionnel
    Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • proof_points · array · optionnel
  • target_lanes · array · optionnel
  • work_history · array · optionnel
  • claims_ledger · array · optionnel
  • voice_profile · string · optionnel
  • auth_token_key · string · optionnel
    Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • database_url_key · string · optionnel
    Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • negative_filters · array · optionnel
  • outreach_history · array · optionnel
  • interview_history · array · optionnel
  • owner_profile_text · string · optionnel
    Private owner profile setup notes. Stored tenant-scoped and never returned raw.
  • resume_variant_ids · array · optionnel
  • travel_preferences · array · optionnel
  • work_style_profile · string · optionnel
    Private, owner-provided work-style guidance. Stored tenant-scoped and never returned raw.
  • application_history · array · optionnel
  • if_match_updated_at · string · optionnel
    Optimistic concurrency guard. Required for every update to an existing profile so concurrent merge or replace writes cannot shrink or overwrite stored history.
  • baseline_resume_text · string · optionnel
    Private baseline resume text. Stored tenant-scoped and never returned raw.
  • tenant_database_type · string · optionnel · internal | sovereign_cloud | byoc
    Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.
  • geography_preferences · array · optionnel
  • linkedin_profile_text · string · optionnel
    Private LinkedIn profile paste/export when LinkedIn blocks automated fetch. Stored tenant-scoped and never returned raw.
  • compensation_preferences · array · optionnel
  • replace_string_array_fields · array · optionnel
    Replace only the named preference array under if_match_updated_at. Use for a superseding travel policy without replacing profile history or other preference arrays.

  Exemple d'appel

  {"name": "talent_scout_my_profile_upsert", "arguments": {"mode": "merge", "dry_run": true, "tenant_id": "texte", "sqlite_path": "texte", "proof_points": [], "target_lanes": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_person_research_notes≈ 446 tokens

  Generate public contact-research labels and safe LinkedIn search queries so the account owner can decide who to review manually. No LinkedIn scraping, no auto-connect, no auto-message; human review required.

  Paramètres, retour & exemple (10)

  Paramètres

  • limit · integer · optionnel
  • role_lane · string · optionnel
  • tenant_id · string · optionnel
  • campaign_id · string · optionnel
  • sqlite_path · string · optionnel
    Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • company_name · string · optionnel
  • auth_token_key · string · optionnel
    Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • database_url_key · string · optionnel
    Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • company_target_id · string · optionnel
  • tenant_database_type · string · optionnel · internal | sovereign_cloud | byoc
    Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.

  Exemple d'appel

  {"name": "talent_scout_person_research_notes", "arguments": {"limit": 1, "role_lane": "texte", "tenant_id": "texte", "campaign_id": "texte", "sqlite_path": "texte", "company_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_pipeline_describe≈ 193 tokens

  Return a compact Talent Scout readiness receipt: pipeline version, surface mode, callable tool groups, and manual-review safety flags. Read-only.

  Paramètres, retour & exemple (1)

  Paramètres

  • tenant_id · string · optionnel

  Exemple d'appel

  {"name": "talent_scout_pipeline_describe", "arguments": {"tenant_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_profile_status≈ 430 tokens

  Read a compact, redacted readiness receipt for the account owner's private Talent Scout profile setup, including profile_version_updated_at for guarded writes through either public profile-upsert alias. Returns only setup status, compose readiness, and active search-rail readiness; never returns raw resume, LinkedIn, work history, claims, or private owner profile text.

  Paramètres, retour & exemple (5)

  Paramètres

  • tenant_id · string · optionnel
  • sqlite_path · string · optionnel
    Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • auth_token_key · string · optionnel
    Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • database_url_key · string · optionnel
    Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • tenant_database_type · string · optionnel · internal | sovereign_cloud | byoc
    Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.

  Exemple d'appel

  {"name": "talent_scout_profile_status", "arguments": {"tenant_id": "texte", "sqlite_path": "texte", "auth_token_key": "texte", "database_url_key": "texte", "tenant_database_type": "internal"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_profile_upsert≈ 1065 tokens

  Create or update the account owner's private Talent Scout profile setup once so compose, fit, and packet tools can reuse self-entered resume, LinkedIn, proof-point, preference, and voice evidence without re-pasting it for every role. Existing profiles require the current profile_version_updated_at from Talent Scout My Profile Status as if_match_updated_at. Stores private owner evidence for proof mapping and never returns raw resume or LinkedIn text.

  Paramètres, retour & exemple (26)

  Paramètres

  • mode · string · optionnel · merge | replace
  • dry_run · boolean · optionnel
    Preview the redacted owner-profile update without writing stored resume, LinkedIn, proof, or rail evidence. Use this for connector smoke tests.
  • tenant_id · string · optionnel
  • sqlite_path · string · optionnel
    Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • proof_points · array · optionnel
  • target_lanes · array · optionnel
  • work_history · array · optionnel
  • claims_ledger · array · optionnel
  • voice_profile · string · optionnel
  • auth_token_key · string · optionnel
    Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • database_url_key · string · optionnel
    Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • negative_filters · array · optionnel
  • outreach_history · array · optionnel
  • interview_history · array · optionnel
  • owner_profile_text · string · optionnel
    Private owner profile setup notes. Stored tenant-scoped and never returned raw.
  • resume_variant_ids · array · optionnel
  • travel_preferences · array · optionnel
  • work_style_profile · string · optionnel
    Private, owner-provided work-style guidance. Stored tenant-scoped and never returned raw.
  • application_history · array · optionnel
  • if_match_updated_at · string · optionnel
    Optimistic concurrency guard. Required for every update to an existing profile so concurrent merge or replace writes cannot shrink or overwrite stored history.
  • baseline_resume_text · string · optionnel
    Private baseline resume text. Stored tenant-scoped and never returned raw.
  • tenant_database_type · string · optionnel · internal | sovereign_cloud | byoc
    Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.
  • geography_preferences · array · optionnel
  • linkedin_profile_text · string · optionnel
    Private LinkedIn profile paste/export when LinkedIn blocks automated fetch. Stored tenant-scoped and never returned raw.
  • compensation_preferences · array · optionnel
  • replace_string_array_fields · array · optionnel
    Replace only the named preference array under if_match_updated_at. Use for a superseding travel policy without replacing profile history or other preference arrays.

  Exemple d'appel

  {"name": "talent_scout_profile_upsert", "arguments": {"mode": "merge", "dry_run": true, "tenant_id": "texte", "sqlite_path": "texte", "proof_points": [], "target_lanes": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_reconcile_application_history≈ 688 tokens

  Correct an owner-reported application-history state with optimistic concurrency and an append-only reconciliation receipt. Use this when an intake or imported record was incorrectly shown as applied. Preserves the history record for audit, removes not-applied records from the active application queue, and never applies, sends, or contacts anyone.

  Paramètres, retour & exemple (8)

  Paramètres

  • dry_run · boolean · optionnel
    Preview matched history records and the redacted reconciliation receipt without writing.
  • tenant_id · string · requis
  • corrections · array · requis
  • sqlite_path · string · optionnel
    Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • auth_token_key · string · optionnel
    Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • database_url_key · string · optionnel
    Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • if_match_updated_at · string · requis
    The exact profile_version_updated_at from applicant_profile_status. A stale value is rejected.
  • tenant_database_type · string · optionnel · internal | sovereign_cloud | byoc
    Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.

  Exemple d'appel

  {"name": "talent_scout_reconcile_application_history", "arguments": {"tenant_id": "texte", "corrections": [], "if_match_updated_at": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_record_application≈ 578 tokens

  Record that the human manually submitted an application. A known Talent Scout queue item is preferred, but a human-attested company, title, requisition/application id, and application URL can create the same durable history-backed queue record when no live posting exists. This updates lifecycle status, schedules follow-up tasks, and records a submission receipt only; it never applies, sends, clicks, or submits anything automatically.

  Paramètres, retour & exemple (12)

  Paramètres

  • send · boolean · optionnel
  • apply · boolean · optionnel
  • notes · string · optionnel
    Optional human note stored in the receipt response only.
  • title · string · optionnel
    Human-attested role title when no queue_item_id exists.
  • company · string · optionnel
    Required with title, requisition_id/application_id, and apply_url when no queue_item_id exists.
  • actor_id · string · optionnel
    Optional actor label for the manual receipt.
  • apply_url · string · optionnel
    Exact human-attested application or employer portal URL. It is retained as provenance, not live-verification proof.
  • tenant_id · string · optionnel
  • submitted_at · string · optionnel
    Optional ISO timestamp for the manual submission. Defaults to now.
  • queue_item_id · string · optionnel
    Talent Scout queue item that Robert manually submitted.
  • application_id · string · optionnel
    Human-attested application identifier; used when a requisition_id is unavailable.
  • requisition_id · string · optionnel
    Human-attested requisition or employer application identifier when no queue_item_id exists.

  Exemple d'appel

  {"name": "talent_scout_record_application", "arguments": {"send": true, "apply": true, "notes": "texte", "title": "texte", "company": "texte", "actor_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_record_manual_note≈ 820 tokens

  Record a human decision and receipt on a Talent Scout manual-note draft. This is closed-world tracking only: it never sends email, LinkedIn messages, phone calls, or applications automatically. Use sent_text only to store text the human already handled manually.

  Paramètres, retour & exemple (28)

  Paramètres

  • goal · string · optionnel · applied_follow_up | exploratory_intro | referral_path
  • send · boolean · optionnel
  • apply · boolean · optionnel
  • notes · string · optionnel
  • channel · string · optionnel · linkedin | email | sms | phone | in_person
  • summary · string · optionnel
    Factual summary of the already-completed human outreach.
  • decision · string · requis · approved_for_manual_send | copied_for_manual_send | edit_requested | rejected | sent_manually_reported | follow_up_due | accepted | replied
    Human decision to record. No option sends anything automatically.
  • sent_text · string · optionnel
    Exact text the human actually sent manually. Talent Scout stores this receipt but never sends it.
  • tenant_id · string · optionnel
  • draft_text · string · optionnel
  • role_title · string · optionnel
  • campaign_id · string · optionnel
  • occurred_at · string · optionnel
    ISO-8601 time the human completed the outreach.
  • person_name · string · optionnel
  • sqlite_path · string · optionnel
    Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • company_name · string · optionnel
  • contact_name · string · optionnel
  • person_label · string · optionnel
  • next_touch_at · string · optionnel
    Optional ISO-8601 next human follow-up time.
  • queue_item_id · string · optionnel
  • application_id · string · optionnel
  • auth_token_key · string · optionnel
    Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • manual_note_id · string · requis
  • idempotency_key · string · optionnel
    Caller-stable key for the immutable relationship receipt.
  • database_url_key · string · optionnel
    Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • company_target_id · string · optionnel
  • edited_draft_text · string · optionnel
  • tenant_database_type · string · optionnel · internal | sovereign_cloud | byoc
    Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.

  Exemple d'appel

  {"name": "talent_scout_record_manual_note", "arguments": {"decision": "approved_for_manual_send", "manual_note_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_record_queue_decision≈ 478 tokens

  Record the account owner's manual decision on an existing Talent Scout queue item: keep, top priority, hold/revisit, pass, or not-a-fit. This is closed-world queue bookkeeping only; it never sends outreach, applies, clicks, submits, screens people, ranks people for hiring, or contacts anyone.

  Paramètres, retour & exemple (10)

  Paramètres

  • send · boolean · optionnel
  • apply · boolean · optionnel
  • title · string · optionnel
    Exact role title lookup when queue_item_id is not known.
  • reason · string · optionnel
    Human note explaining the decision.
  • company · string · optionnel
    Exact company lookup when queue_item_id is not known.
  • actor_id · string · optionnel
    Optional actor label for the manual receipt.
  • decision · string · requis · keep | top_priority | hold | revisit | pass | not_a_fit
    Manual owner decision. pass/not_a_fit suppress the row from active review unless include_archived is requested.
  • tenant_id · string · optionnel
  • queue_item_id · string · optionnel
    Preferred exact Talent Scout queue item id.
  • revisit_after · string · optionnel
    Optional ISO date/time or human-readable revisit cue for hold/revisit decisions.

  Exemple d'appel

  {"name": "talent_scout_record_queue_decision", "arguments": {"decision": "keep"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_record_relationship_activity≈ 724 tokens

  Record one human-reported email, LinkedIn, SMS, call, or visit in the existing StackFast Relationship Core. Returns an immutable, idempotent receipt and makes follow-up state visible in Talent Scout. It never sends, scrapes, applies, submits, or changes candidacy status.

  Paramètres, retour & exemple (16)

  Paramètres

  • channel · string · requis · email | linkedin | sms | call | visit
  • company · string · requis
  • summary · string · requis
    Factual summary of the already-completed human activity (maximum 5,000 characters; longer input is rejected and never silently truncated).
  • direction · string · requis · inbound | outbound | lifecycle
    Explicitly state whether the employer/contact initiated this activity, the candidate initiated it, or it is a system lifecycle event. No direction is inferred.
  • tenant_id · string · requis
  • occurred_at · string · requis
    ISO-8601 timestamp for the human-completed activity.
  • sqlite_path · string · optionnel
    Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • artifact_url · string · optionnel
    Optional governed evidence URL; no artifact body is copied.
  • contact_name · string · requis
  • next_touch_at · string · optionnel
    Optional ISO-8601 follow-up time.
  • auth_token_key · string · optionnel
    Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • idempotency_key · string · requis
    Caller-stable key that makes retries return the original immutable receipt.
  • database_url_key · string · optionnel
    Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • tenant_database_type · string · optionnel · internal | sovereign_cloud | byoc
    Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.
  • related_queue_item_id · string · optionnel
  • related_application_id · string · optionnel

  Exemple d'appel

  {"name": "talent_scout_record_relationship_activity", "arguments": {"channel": "email", "company": "texte", "summary": "texte", "direction": "inbound", "tenant_id": "texte", "occurred_at": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_review_queue≈ 728 tokens

  Read the account owner's own first-party Talent Scout job-search work queue for real synced board roles, draft opportunities, packets, follow-up items, and the daily reconciliation report. This is not an employer review queue, applicant screening queue, candidate ranking system, or hiring decision tool. Mailbox reconciliation runs server-side via the StackFast service-account reader. Clients MUST NOT invoke their own Gmail/email connector; if mailbox_reconciliation_status is not ok, surface the red receipt and stop instead of substituting a client-side mailbox read. Surfaces open roles, direct-URL verification needs, waiting/follow-up buckets, preference filters, and today's slate. Robert's connector resolves to tenant robert and demo rows are quarantined away. Review only; no sends or applications.

  Paramètres, retour & exemple (12)

  Paramètres

  • limit · integer · optionnel
  • run_id · string · optionnel
  • status · string · optionnel
  • compact · boolean · optionnel
    Return compact queue metadata and a daily_pipeline_summary instead of heavy control-tower sections.
  • profile · object · optionnel
    Alias for owner_profile when reviewing stale queue items.
  • tenant_id · string · optionnel
  • include_items · boolean · optionnel
    When false, return health/counts/timing only without loading queue item payloads. Use for fast connector smoke tests.
  • owner_profile · object · optionnel
    Optional owner preference context used to refresh stale zero-score queue items inside this tenant only.
  • include_detail · boolean · optionnel
    When true, include full queue item payloads. Defaults false so hosted MCP review_queue stays small and fast.
  • include_applied · boolean · optionnel
    Include already-applied rows. Defaults false unless explicitly reviewing follow-up history.
  • include_archived · boolean · optionnel
    Include archived, rejected, passed, stale, or already-applied rows. Defaults false for active work queues.
  • include_sync_delta · boolean · optionnel
    When true, include a guarded scout.import_delta-compatible cloud-to-BYOC queue sync payload. Defaults false.

  Exemple d'appel

  {"name": "talent_scout_review_queue", "arguments": {"limit": 1, "run_id": "texte", "status": "texte", "compact": true, "profile": {}, "tenant_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_role_review≈ 338 tokens

  Compare a role text with the account owner's own saved preferences using a deterministic checklist so Robert can decide whether to review or apply manually. Returns transparent self-review data; no outbound action.

  Paramètres, retour & exemple (6)

  Paramètres

  • target · object · optionnel
    Structured role text or object.
  • profile · object · optionnel
    Optional owner profile. Defaults to Robert's safe Talent Scout profile for public connector smoke tests.
  • tenant_id · string · optionnel
  • target_text · string · optionnel
    Plain-language target role text for lightweight connector smoke tests.
  • owner_profile · object · optionnel
    Alias for profile.
  • min_review_threshold · integer · optionnel

  Exemple d'appel

  {"name": "talent_scout_role_review", "arguments": {"target": {}, "profile": {}, "tenant_id": "texte", "target_text": "texte", "owner_profile": {}, "min_review_threshold": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_scan_company_for_roles≈ 712 tokens

  Preview a qualified company target for direct careers URLs and role-lane matches. Returns verified status receipts such as company_careers_open_role, needs_human_url_verification, needs_jd_hydration, or careers_page_no_relevant_role. Read-only by default: it returns exact role records for human review, does not persist queue rows unless persist_results is explicitly true, and never invents jobs.

  Paramètres, retour & exemple (18)

  Paramètres

  • limit · integer · optionnel
  • tenant_id · string · optionnel
  • source_url · string · optionnel
  • campaign_id · string · optionnel
  • careers_url · string · optionnel
  • sqlite_path · string · optionnel
    Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • company_name · string · optionnel
  • target_lanes · array · optionnel
  • auth_token_key · string · optionnel
    Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • company_domain · string · optionnel
    Backward-compatible alias for company_homepage_url; bare domains are normalized to https://<domain>.
  • persist_results · boolean · optionnel
    When true, persist verified role records and role-scan receipts to Talent Scout. Defaults false so hosted MCP scans remain read-only previews for human review.
  • database_url_key · string · optionnel
    Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • company_target_id · string · optionnel
  • target_role_lanes · array · optionnel
  • eligible_countries · array · optionnel
  • allow_live_firecrawl · boolean · optionnel
    Backward-compatible no-op for this scanner; official ATS/API scans are preferred when available.
  • company_homepage_url · string · optionnel
  • tenant_database_type · string · optionnel · internal | sovereign_cloud | byoc
    Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.

  Exemple d'appel

  {"name": "talent_scout_scan_company_for_roles", "arguments": {"limit": 1, "tenant_id": "texte", "source_url": "texte", "campaign_id": "texte", "careers_url": "texte", "sqlite_path": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_score_fit≈ 337 tokens

  Compare a role text with the account owner's own saved preferences using a deterministic checklist so Robert can decide whether to review or apply manually. Returns transparent self-review data; no outbound action.

  Paramètres, retour & exemple (6)

  Paramètres

  • target · object · optionnel
    Structured role text or object.
  • profile · object · optionnel
    Optional owner profile. Defaults to Robert's safe Talent Scout profile for public connector smoke tests.
  • tenant_id · string · optionnel
  • target_text · string · optionnel
    Plain-language target role text for lightweight connector smoke tests.
  • owner_profile · object · optionnel
    Alias for profile.
  • min_review_threshold · integer · optionnel

  Exemple d'appel

  {"name": "talent_scout_score_fit", "arguments": {"target": {}, "profile": {}, "tenant_id": "texte", "target_text": "texte", "owner_profile": {}, "min_review_threshold": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_search_opportunities≈ 451 tokens

  Run fresh governed public-opportunity discovery for the account owner to find roles they may review and apply to manually. If live discovery is unavailable or empty, returns fresh_discovery_count: 0 and does not substitute the existing review queue. Draft/review only; never applies or sends messages.

  Paramètres, retour & exemple (9)

  Paramètres

  • lane · string · optionnel · J | C
  • limit · integer · optionnel
  • query · string · requis
    Plain-language opportunity search.
  • sources · array · optionnel
  • min_score · integer · optionnel
  • tenant_id · string · optionnel
  • owner_profile · object · optionnel
    Safe owner preference facts and positioning for local review.
  • include_tracked · boolean · optionnel
    When true, include tracked-board comparison metadata. Search results still do not return the review queue.
  • allow_live_firecrawl · boolean · optionnel
    Run the approved live-discovery adapter. Costs are governed by the FireCrawl budget gate and kill switch.

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_set_search_rails≈ 590 tokens

  Persist the active Talent Scout search strategy for a tenant: target lanes, compensation floor, geography, positive/negative filters, resume-variant priority, travel posture, and voice anchor. Future search, fit, review, compose, packet, and note calls load these rails by default until superseded.

  Paramètres, retour & exemple (18)

  Paramètres

  • active · boolean · optionnel
  • reason · string · optionnel
  • priority · string · optionnel
  • geography · array · optionnel
  • rail_name · string · requis
  • tenant_id · string · optionnel
  • sqlite_path · string · optionnel
    Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • age_strategy · object · optionnel
  • target_lanes · array · optionnel
  • voice_anchor · string · optionnel
  • auth_token_key · string · optionnel
    Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • database_url_key · string · optionnel
    Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • negative_filters · array · optionnel
  • owner_profile_id · string · optionnel
  • positive_filters · array · optionnel
  • compensation_floor · string · optionnel
  • tenant_database_type · string · optionnel · internal | sovereign_cloud | byoc
    Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.
  • resume_variant_priority · object · optionnel

  Exemple d'appel

  {"name": "talent_scout_set_search_rails", "arguments": {"rail_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• talent_scout_upsert_campaign_profile≈ 835 tokens

  Create, update, activate, pause, or archive a saved Talent Scout direct-company discovery campaign. Campaigns define company lanes, role lanes, size, geography, comp floor, travel tolerance, negative filters, resume variant, voice anchor, and human-review requirements. Draft/review only; never sends or applies.

  Paramètres, retour & exemple (27)

  Paramètres

  • name · string · optionnel
  • status · string · optionnel · active | paused | archived
  • priority · string · optionnel
  • tenant_id · string · optionnel
  • campaign_id · string · optionnel
  • sqlite_path · string · optionnel
    Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • update_mode · string · optionnel · patch | replace
    Patch preserves omitted fields. Replace is explicit and may reapply defaults.
  • voice_anchor · string · optionnel
  • auth_token_key · string · optionnel
    Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • radius_minutes · integer · optionnel
  • company_size_max · integer · optionnel
  • company_size_min · integer · optionnel
  • compensation_min · string · optionnel
  • contact_strategy · object · optionnel
  • database_url_key · string · optionnel
    Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • expanded_regions · array · optionnel
  • expected_version · string · optionnel
    Optional optimistic concurrency token from campaign.updated_at. A mismatch fails without writing.
  • geography_anchor · string · optionnel
  • negative_filters · array · optionnel
  • target_role_lanes · array · optionnel
  • eligible_countries · array · optionnel
    Backward-compatible campaign-level work-authorization hint. The stored owner policy still owns the hard country gate.
  • minimum_total_comp · integer · optionnel
  • seed_robert_campaign · boolean · optionnel
  • target_company_lanes · array · optionnel
  • tenant_database_type · string · optionnel · internal | sovereign_cloud | byoc
    Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.
  • acceptable_structures · array · optionnel
  • resume_variant_strategy · object · optionnel

  Exemple d'appel

  {"name": "talent_scout_upsert_campaign_profile", "arguments": {"name": "texte", "status": "active", "priority": "texte", "tenant_id": "texte", "campaign_id": "texte", "sqlite_path": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "public_tool": "texte", "drafts_never_sends": true, "no_autonomous_outbound": true}}

• voice_intelligence_run≈ 1437 tokens

  Run the voice intelligence orchestrator over any input: an uploaded or recorded audio/video file (base64 in file), a public audio or video URL (audio_or_video_url), a PDF (pdf), an image (image), or raw text/notes (text and/or notes). Provide exactly ONE input carrier — audio_or_video_url, file, pdf, image, or text/notes. The input is normalized to a transcript via the existing transcription rails, then three composed outputs are returned: a condensed summary (with action items, decisions, and a next step), a full-verbatim polished actual script (filler removed, wording preserved, never paraphrased; call sources return a masked summary instead), and an authority report (content flywheel plan, plus an owner-facing business report when business context is provided). All outward outputs are mask-gated.

  Paramètres, retour & exemple (11)

  Paramètres

  • pdf · object · optionnel
    PDF document payload, base64-encoded. One of the five input carriers.
  • file · object · optionnel
    Uploaded or recorded audio/video (or text-carrying) file payload, base64-encoded. One of the five input carriers.
  • text · string · optionnel
    Raw text input (transcription skipped). One of the five input carriers.
  • image · object · optionnel
    Image payload, base64-encoded. One of the five input carriers.
  • notes · string · optionnel
    Alias for text input; merged with text when both are present. Counts as the text carrier.
  • title · string · optionnel
    Optional title for the source material.
  • source · string · optionnel · upload | recording | call | document | text
    Optional input provenance. 'call' sources return a masked-summary actual script instead of full verbatim.
  • speaker · string · optionnel
    Optional primary speaker name.
  • business · object · optionnel
    Optional GrowthOS business context. Providing business_name enables the owner-facing business report inside the authority report.
  • identity · object · optionnel
    Optional local identity used by the owner-facing business report.
  • audio_or_video_url · string · optionnel
    Public audio or video URL to transcribe (YouTube caption rail or upload transcription). One of the five input carriers.

  Exemple d'appel

  {"name": "voice_intelligence_run", "arguments": {"pdf": {}, "file": {}, "text": "texte", "image": {}, "notes": "texte", "title": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"llm": {}, "summary": {}, "receipts": [], "input_kind": "audio_video_url", "transcript": "texte", "actual_script": {}, "schema_version": "texte", "authority_report": {}, "transcript_source": "youtube_captions"}}

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://stackfast.ai/api/mcp