StackFast FractWin Expert Brain

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Expert knowledge base for sales, negotiation, strategy, operations, and risk.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "StackFast FractWin Expert Brain": {
      "url": "https://stackfast.ai/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (74)

• session_file_read read-only

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

  Parameters:

  • limit — integer
  • filename — string
  • session_id — string
  • artifact_id — integer

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• credentials_inventory read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• dealership_check_lead_follow_up read-only

  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.

  Parameters:

  • mode (required) — string
  • stop — object
  • tenant_id — string
  • evaluation — object
  • fixture_id — string
  • governance — object

  Hints: read-only yes · destructive no · idempotent no · open-world no

• dealership_sales_floor_brief read-only

  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.

  Parameters:

  • workflow (required) — string
  • mode — string
  • situation — string — Transient operator-described situation. Do not include unnecessary customer identity or protected source material.
  • tenant_id — string — Optional assertion; must match the authenticated tenant.
  • fixture_id — string
  • role_context — string
  • schema_version — string
  • idempotency_key — string
  • opportunity_ref — string — Optional opaque tenant-scoped opportunity reference. The advisor does not resolve or mutate it.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• audit_status read-only

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

  Parameters:

  • audit_project_id (required) — string
  • tenant_id — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• artifact_generate read-only

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

  Parameters:

  • tenant_id (required) — string
  • artifact_type (required) — string
  • lane — string
  • format — string
  • locale — string
  • audience — string
  • caller_type — string
  • brand_kit_id — string
  • voice_anchor — string
  • budget_policy — object
  • variant_count — integer
  • source_context — ['object', 'string']
  • idempotency_key — string
  • output_language — string
  • variant_strategy — string
  • voice_profile_id — string
  • analysis_findings — array

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• artifact_refine read-only

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

  Parameters:

  • tenant_id (required) — string
  • refinement_instruction (required) — string
  • lane — string
  • format — string
  • audience — string
  • draft_id — string
  • artifact_type — string
  • source_content — string
  • source_context — ['object', 'string']
  • idempotency_key — string
  • new_source_context — ['object', 'string']

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• artifact_save read-only

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

  Parameters:

  • tenant_id (required) — string
  • draft_id (required) — string
  • approved — boolean
  • reuse_tags — array
  • learning_scope — string
  • idempotency_key — string
  • approval_event_id — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• artifact_export read-only

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

  Parameters:

  • tenant_id (required) — string
  • target (required) — string
  • format — string
  • draft_id — string
  • artifact_id — string
  • target_config — object
  • idempotency_key — string
  • approval_event_id — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• reply_compose read-only

  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.

  Parameters:

  • channel (required) — string
  • goal — string
  • surface — string
  • signature — string
  • tenant_id — string
  • constraints — object
  • crm_context — object
  • referred_by — string
  • recipient_name — string
  • idempotency_key — string
  • inbound_message — string
  • persist_artifact — boolean
  • capability_context — string
  • relationship_context — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• artifact_audit read-only

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

  Parameters:

  • tenant_id (required) — string
  • draft_id — string
  • artifact_id — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• growthos_scorecard read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• growthos_business_brain_interview read-only

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

  Parameters:

  • action — string
  • source — string
  • answers — array
  • company — string
  • lead_id — ['string', 'number']
  • tenant_id — string
  • session_id — string
  • customer_name — string
  • customer_email — string
  • interview_type — string
  • audit_project_id — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• growthos_revenue_capture_packet read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• growthos_owner_facing_report read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• growthos_opportunity_scout_packet read-only

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

  Parameters:

  • opportunity (required) — object — Opportunity input. opportunity_type must be one of the registered Opportunity Scout types.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• growthos_digital_clone_packet read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• cogentcast_package_preview read-only

  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.

  Parameters:

  • input (required) — object — 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.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• cogentcast_package_create read-only

  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.

  Parameters:

  • preview_digest (required) — string
  • input — object — 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
  • idempotency_key — string — Caller-stable key for this single create operation. Exact replays return the stored result; a different key is rejected.
  • preview_reference — string — Opaque short-lived reference returned by package.preview.
  • content_fingerprint — string — Exact immutable metadata/source fingerprint returned by package.preview.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• cogentcast_production_run read-only

  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.

  Parameters:

  • package_id (required) — string
  • stage (required) — string
  • idempotency_key (required) — string
  • chunk_id — string
  • segment_id — string
  • dispatch_id — string
  • sample_scope — string
  • manifest_sha256 — string
  • verifier_job_id — string
  • verification_task_id — string

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• cogentcast_production_status read-only

  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.

  Parameters:

  • package_id (required) — string — ws_, ccnr_, or ccaud_ package identifier.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• cogentcast_approval_resolve read-only

  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.

  Parameters:

  • package_id (required) — string
  • approval_receipt_id (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• estimator_catalog_search read-only

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

  Parameters:

  • line — object
  • lines — array
  • query — string
  • bridge — object
  • format — string
  • approval — object
  • source_id — string
  • tenant_id — string — Tenant boundary, for example repair-remodel-360.
  • adapter_id — string — Vertical adapter.
  • document_id — string
  • estimate_id — string
  • progress_pct — number
  • idempotency_key — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• estimator_catalog_sources read-only

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

  Parameters:

  • line — object
  • lines — array
  • query — string
  • bridge — object
  • format — string
  • approval — object
  • source_id — string
  • tenant_id — string — Tenant boundary, for example repair-remodel-360.
  • adapter_id — string — Vertical adapter.
  • document_id — string
  • estimate_id — string
  • progress_pct — number
  • idempotency_key — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• estimator_estimate_create_draft read-only

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

  Parameters:

  • line — object
  • lines — array
  • query — string
  • bridge — object
  • format — string
  • approval — object
  • source_id — string
  • tenant_id — string — Tenant boundary, for example repair-remodel-360.
  • adapter_id — string — Vertical adapter.
  • document_id — string
  • estimate_id — string
  • progress_pct — number
  • idempotency_key — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• estimator_estimate_add_line read-only

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

  Parameters:

  • line — object
  • lines — array
  • query — string
  • bridge — object
  • format — string
  • approval — object
  • source_id — string
  • tenant_id — string — Tenant boundary, for example repair-remodel-360.
  • adapter_id — string — Vertical adapter.
  • document_id — string
  • estimate_id — string
  • progress_pct — number
  • idempotency_key — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• estimator_estimate_update_line read-only

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

  Parameters:

  • line — object
  • lines — array
  • query — string
  • bridge — object
  • format — string
  • approval — object
  • source_id — string
  • tenant_id — string — Tenant boundary, for example repair-remodel-360.
  • adapter_id — string — Vertical adapter.
  • document_id — string
  • estimate_id — string
  • progress_pct — number
  • idempotency_key — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• estimator_estimate_convert_to_bid read-only

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

  Parameters:

  • line — object
  • lines — array
  • query — string
  • bridge — object
  • format — string
  • approval — object
  • source_id — string
  • tenant_id — string — Tenant boundary, for example repair-remodel-360.
  • adapter_id — string — Vertical adapter.
  • document_id — string
  • estimate_id — string
  • progress_pct — number
  • idempotency_key — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• estimator_estimate_convert_to_invoice read-only

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

  Parameters:

  • line — object
  • lines — array
  • query — string
  • bridge — object
  • format — string
  • approval — object
  • source_id — string
  • tenant_id — string — Tenant boundary, for example repair-remodel-360.
  • adapter_id — string — Vertical adapter.
  • document_id — string
  • estimate_id — string
  • progress_pct — number
  • idempotency_key — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• estimator_estimate_progress_invoice read-only

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

  Parameters:

  • line — object
  • lines — array
  • query — string
  • bridge — object
  • format — string
  • approval — object
  • source_id — string
  • tenant_id — string — Tenant boundary, for example repair-remodel-360.
  • adapter_id — string — Vertical adapter.
  • document_id — string
  • estimate_id — string
  • progress_pct — number
  • idempotency_key — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• estimator_estimate_export read-only

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

  Parameters:

  • line — object
  • lines — array
  • query — string
  • bridge — object
  • format — string
  • approval — object
  • source_id — string
  • tenant_id — string — Tenant boundary, for example repair-remodel-360.
  • adapter_id — string — Vertical adapter.
  • document_id — string
  • estimate_id — string
  • progress_pct — number
  • idempotency_key — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• estimator_policy_check read-only

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

  Parameters:

  • line — object
  • lines — array
  • query — string
  • bridge — object
  • format — string
  • approval — object
  • source_id — string
  • tenant_id — string — Tenant boundary, for example repair-remodel-360.
  • adapter_id — string — Vertical adapter.
  • document_id — string
  • estimate_id — string
  • progress_pct — number
  • idempotency_key — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• estimator_receipt_get read-only

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

  Parameters:

  • line — object
  • lines — array
  • query — string
  • bridge — object
  • format — string
  • approval — object
  • source_id — string
  • tenant_id — string — Tenant boundary, for example repair-remodel-360.
  • adapter_id — string — Vertical adapter.
  • document_id — string
  • estimate_id — string
  • progress_pct — number
  • idempotency_key — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• ai_receptionist_status read-only

  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.

  Parameters:

  • call_id (required) — string
  • tenant_id — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• ai_receptionist_review_queue read-only

  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.

  Parameters:

  • limit — integer
  • tenant_id — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• ai_receptionist_callback_packet read-only

  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.

  Parameters:

  • call_id (required) — string
  • tenant_id — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• talent_scout_my_profile_upsert read-only

  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.

  Parameters:

  • mode — string
  • dry_run — boolean — Preview the redacted owner-profile update without writing stored resume, LinkedIn, proof, or rail evidence. Use this for connector smoke tests.
  • tenant_id — string
  • sqlite_path — string — Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • proof_points — array
  • target_lanes — array
  • work_history — array
  • claims_ledger — array
  • voice_profile — string
  • auth_token_key — string — Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • database_url_key — string — Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • negative_filters — array
  • outreach_history — array
  • interview_history — array
  • owner_profile_text — string — Private owner profile setup notes. Stored tenant-scoped and never returned raw.
  • resume_variant_ids — array
  • travel_preferences — array
  • work_style_profile — string — Private, owner-provided work-style guidance. Stored tenant-scoped and never returned raw.
  • application_history — array
  • if_match_updated_at — string — 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 — Private baseline resume text. Stored tenant-scoped and never returned raw.
  • tenant_database_type — string — 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
  • linkedin_profile_text — string — Private LinkedIn profile paste/export when LinkedIn blocks automated fetch. Stored tenant-scoped and never returned raw.
  • compensation_preferences — array
  • replace_string_array_fields — array — 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.

  Hints: read-only yes · destructive no · idempotent no · open-world no

• talent_scout_profile_upsert read-only

  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.

  Parameters:

  • mode — string
  • dry_run — boolean — Preview the redacted owner-profile update without writing stored resume, LinkedIn, proof, or rail evidence. Use this for connector smoke tests.
  • tenant_id — string
  • sqlite_path — string — Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • proof_points — array
  • target_lanes — array
  • work_history — array
  • claims_ledger — array
  • voice_profile — string
  • auth_token_key — string — Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • database_url_key — string — Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • negative_filters — array
  • outreach_history — array
  • interview_history — array
  • owner_profile_text — string — Private owner profile setup notes. Stored tenant-scoped and never returned raw.
  • resume_variant_ids — array
  • travel_preferences — array
  • work_style_profile — string — Private, owner-provided work-style guidance. Stored tenant-scoped and never returned raw.
  • application_history — array
  • if_match_updated_at — string — 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 — Private baseline resume text. Stored tenant-scoped and never returned raw.
  • tenant_database_type — string — 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
  • linkedin_profile_text — string — Private LinkedIn profile paste/export when LinkedIn blocks automated fetch. Stored tenant-scoped and never returned raw.
  • compensation_preferences — array
  • replace_string_array_fields — array — 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.

  Hints: read-only yes · destructive no · idempotent no · open-world no

• talent_scout_my_profile_status read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• talent_scout_profile_status read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• talent_scout_reconcile_application_history read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent no · open-world no

• talent_scout_set_search_rails read-only

  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.

  Parameters:

  • rail_name (required) — string
  • active — boolean
  • reason — string
  • priority — string
  • geography — array
  • tenant_id — string
  • sqlite_path — string — Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • age_strategy — object
  • target_lanes — array
  • voice_anchor — string
  • auth_token_key — string — Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • database_url_key — string — Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • negative_filters — array
  • owner_profile_id — string
  • positive_filters — array
  • compensation_floor — string
  • tenant_database_type — string — 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

  Hints: read-only yes · destructive no · idempotent no · open-world no

• talent_scout_upsert_campaign_profile read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent no · open-world no

• talent_scout_discover_companies_by_campaign read-only

  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.

  Parameters:

  • limit — integer
  • sources — array
  • tenant_id — string
  • campaign_id — string
  • sqlite_path — string — Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • campaign_name — string
  • auth_token_key — string — Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • persist_results — boolean — 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 — Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • allow_live_firecrawl — boolean — Backward-compatible refresh flag; Firecrawl is only a fallback/search or downstream extraction provider, not the Stage 1 radar.
  • tenant_database_type — string — 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 — 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.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• talent_scout_discover_local_companies read-only

  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.

  Parameters:

  • limit — integer
  • sources — array
  • tenant_id — string
  • campaign_id — string
  • sqlite_path — string — Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • campaign_name — string
  • auth_token_key — string — Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • radius_minutes — integer
  • persist_results — boolean — 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
  • company_size_min — integer
  • database_url_key — string — Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • geography_anchor — string
  • target_role_lanes — array
  • allow_live_firecrawl — boolean — Backward-compatible refresh flag; Firecrawl is only a fallback/search or downstream extraction provider, not the Stage 1 radar.
  • target_company_lanes — array
  • tenant_database_type — string — 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 — Refresh public business website leads through the configured directory provider and distance check. Websites are required before downstream enrichment.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• talent_scout_scan_company_for_roles read-only

  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.

  Parameters:

  • limit — integer
  • tenant_id — string
  • source_url — string
  • campaign_id — string
  • careers_url — string
  • sqlite_path — string — Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • company_name — string
  • target_lanes — array
  • auth_token_key — string — Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • company_domain — string — Backward-compatible alias for company_homepage_url; bare domains are normalized to https://<domain>.
  • persist_results — boolean — 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 — Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • company_target_id — string
  • target_role_lanes — array
  • eligible_countries — array
  • allow_live_firecrawl — boolean — Backward-compatible no-op for this scanner; official ATS/API scans are preferred when available.
  • company_homepage_url — string
  • tenant_database_type — string — Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• talent_scout_person_research_notes read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent no · open-world no

• talent_scout_business_email_receipt read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent no · open-world no

• talent_scout_draft_manual_note read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• talent_scout_record_manual_note read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent no · open-world no

• talent_scout_record_relationship_activity read-only

  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.

  Parameters:

  • tenant_id (required) — string
  • idempotency_key (required) — string — Caller-stable key that makes retries return the original immutable receipt.
  • channel (required) — string
  • direction (required) — string — Explicitly state whether the employer/contact initiated this activity, the candidate initiated it, or it is a system lifecycle event. No direction is inferred.
  • company (required) — string
  • contact_name (required) — string
  • occurred_at (required) — string — ISO-8601 timestamp for the human-completed activity.
  • summary (required) — string — Factual summary of the already-completed human activity (maximum 5,000 characters; longer input is rejected and never silently truncated).
  • sqlite_path — string — Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
  • artifact_url — string — Optional governed evidence URL; no artifact body is copied.
  • next_touch_at — string — Optional ISO-8601 follow-up time.
  • auth_token_key — string — Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
  • database_url_key — string — Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
  • tenant_database_type — string — 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
  • related_application_id — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• talent_scout_correct_relationship_activity read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• talent_scout_record_application read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent no · open-world no

• talent_scout_form_schema_receipt read-only

  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.

  Parameters:

  • fields (required) — array
  • send — boolean
  • apply — boolean
  • submit — boolean
  • tenant_id — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• talent_scout_browser_fill_receipt read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• talent_scout_record_queue_decision read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent no · open-world no

• talent_scout_import_byoc_delta read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent no · open-world no

• talent_scout_pipeline_describe read-only

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

  Parameters:

  • tenant_id — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• talent_scout_search_opportunities read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent no · open-world no

• talent_scout_role_review read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• talent_scout_score_fit read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• talent_scout_explain_preferences_match read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• talent_scout_create_packet read-only

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

  Parameters:

  • queue_item_id (required) — string
  • notes — string
  • actor_id — string
  • tenant_id — string
  • output_kind — string
  • opportunity_mode — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• talent_scout_compose_application read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent no · open-world no

• talent_scout_draft_outreach read-only

  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.

  Parameters:

  • target_name (required) — string
  • pains (required) — array
  • send — boolean
  • apply — boolean
  • tenant_id — string
  • artifact_type — string
  • voice_profile — string
  • voice_samples — array

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• talent_scout_review_queue read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent no · open-world no

• talent_scout_daily_pipeline read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent no · open-world no

• talent_scout_mail_signals read-only

  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.

  Parameters:

  • limit — integer
  • tenant_id — string

  Hints: read-only yes · destructive no · idempotent no · open-world no

• talent_scout_application_workup read-only

  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.

  Parameters:

  • notes — string
  • title — string — Role title lookup when queue_item_id is not known.
  • company — string — Company name lookup when queue_item_id is not known.
  • tenant_id — string
  • queue_item_id — string — Preferred exact Talent Scout queue item id. If omitted, provide company and title.
  • application_id — string — Optional ATS/portal application or requisition id, such as R110984. Resolves only to an existing Talent Scout queue/history record.
  • requisition_id — string — Alias for application_id when the id is a req/requisition id.
  • canonical_job_id — string — Optional canonical job id lookup. Resolves only to an existing Talent Scout queue/history record.
  • job_description_text — string — 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 — Alias for application_id when the id came from an external portal.
  • user_supplied_jd_text — string — Alias for job_description_text. Used as owner-supplied JD evidence only for this governed workup.
  • include_follow_up_plan — boolean
  • include_interview_prep — boolean

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• talent_scout_generate_finished_resume read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent no · open-world no

• voice_intelligence_run read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent no · open-world yes

• search read-only

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

  Parameters:

  • query (required) — string — Natural language search query.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• fetch read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• boot_status read-only

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

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.