# StackFast FractWin Expert Brain (remote · stackfast.ai)

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

- Trust score: 74/100 (medium)
- Change this week: +8
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `stackfast.ai`: 74/100 (this document), [markdown](https://verifymcp.io/servers/trupe-rs-expert-brain/api-mcp.md), [page](https://verifymcp.io/servers/trupe-rs-expert-brain/api-mcp)

## Channel facts

- Endpoint: `https://stackfast.ai/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 94/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 55/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (poor).
  - Context-footprint check failed: tool/resource definitions use about 12369 tokens (~184/item across 67 items; 65 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 81/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 33% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 73/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### Claude

```bash
claude mcp add --transport http trupe-rs-expert-brain https://stackfast.ai/api/mcp
```

### Codex

```toml
[mcp_servers.trupe-rs-expert-brain]
url = "https://stackfast.ai/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "trupe-rs-expert-brain": {
      "type": "remote",
      "url": "https://stackfast.ai/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add trupe-rs-expert-brain --url https://stackfast.ai/api/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  trupe-rs-expert-brain:
    url: "https://stackfast.ai/api/mcp"
```

### Other

```json
{
  "mcpServers": {
    "trupe-rs-expert-brain": {
      "type": "http",
      "url": "https://stackfast.ai/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 73, +8)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 65, −2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 67, 0)

- [cosmetic] “talent_scout_draft_manual_note” added an optional parameter “contact_name”
- [cosmetic] “talent_scout_draft_manual_note” added an optional parameter “application_id”
- [cosmetic] “talent_scout_draft_manual_note” added an optional parameter “company”
- [cosmetic] “talent_scout_draft_manual_note” added an optional parameter “queue_item_id”
- [cosmetic] “talent_scout_draft_manual_note” added an optional parameter “title”

### 2026-07-28 (score 67, +1)

- [cosmetic] “talent_scout_daily_pipeline” added an optional parameter “include_items”

### 2026-07-27 (score 66, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 65)

First indexed and scored.

## MCP tools (65)

### `session_file_read` (~56 tokens)

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

Input parameters:

- `artifact_id` (integer)
- `filename` (string)
- `limit` (integer)
- `session_id` (string)

### `credentials_inventory` (~115 tokens)

Credential Inventory

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.

Input parameters:

- `query` (string): Optional service, provider, env var, or natural-language query such as openai, OPENAI_API_KEY, gmail, Gemini, FireCrawl, or Vercel.

Output parameters:

- `count` (number)
- `entries` (array)
- `ok` (boolean)
- `raw_secret_values_included` (boolean)
- `schema_version` (string)
- `usage` (object)

### `audit_status` (~45 tokens)

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

Input parameters:

- `audit_project_id` (string, required)
- `tenant_id` (string)

### `artifact_generate` (~175 tokens)

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

Input parameters:

- `analysis_findings` (array)
- `artifact_type` (string, required)
- `audience` (string)
- `brand_kit_id` (string)
- `budget_policy` (object)
- `caller_type` (string)
- `format` (string)
- `idempotency_key` (string)
- `lane` (string)
- `locale` (string)
- `output_language` (string)
- `source_context` (object|string)
- `tenant_id` (string, required)
- `variant_count` (integer)
- `variant_strategy` (string)
- `voice_anchor` (string)
- `voice_profile_id` (string)

### `artifact_refine` (~119 tokens)

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

Input parameters:

- `artifact_type` (string)
- `audience` (string)
- `draft_id` (string)
- `format` (string)
- `idempotency_key` (string)
- `lane` (string)
- `new_source_context` (object|string)
- `refinement_instruction` (string, required)
- `source_content` (string)
- `source_context` (object|string)
- `tenant_id` (string, required)

### `artifact_save` (~85 tokens)

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

Input parameters:

- `approval_event_id` (string)
- `approved` (boolean)
- `draft_id` (string, required)
- `idempotency_key` (string)
- `learning_scope` (string)
- `reuse_tags` (array)
- `tenant_id` (string, required)

### `artifact_export` (~94 tokens)

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

Input parameters:

- `approval_event_id` (string)
- `artifact_id` (string)
- `draft_id` (string)
- `format` (string)
- `idempotency_key` (string)
- `target` (string, required)
- `target_config` (object)
- `tenant_id` (string, required)

### `reply_compose` (~157 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.

Input parameters:

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

### `artifact_audit` (~57 tokens)

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

Input parameters:

- `artifact_id` (string)
- `draft_id` (string)
- `tenant_id` (string, required)

### `growthos_scorecard` (~97 tokens)

GrowthOS Scorecard

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.

Input parameters:

- `prospect` (object): Single local-business prospect input.
- `prospects` (array): Batch of up to 25 local-business prospect inputs.
- `sender` (object): Optional sender identity with sender_name and geography.

Output parameters:

- `no_autonomous_outbound` (boolean)
- `ok` (boolean)
- `public_name` (string)
- `review_required_before_send` (boolean)
- `tool` (string)

### `growthos_business_brain_interview` (~124 tokens)

GrowthOS Business Brain Interview

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

Input parameters:

- `action` (string)
- `answers` (array)
- `audit_project_id` (string)
- `company` (string)
- `customer_email` (string)
- `customer_name` (string)
- `interview_type` (string)
- `lead_id` (string|number)
- `session_id` (string)
- `source` (string)
- `tenant_id` (string)

Output parameters:

- `no_autonomous_outbound` (boolean)
- `ok` (boolean)
- `public_name` (string)
- `review_required_before_send` (boolean)
- `tool` (string)

### `growthos_revenue_capture_packet` (~149 tokens)

GrowthOS Revenue Capture Packet

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.

Input parameters:

- `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.
- `prospect` (object, required)
- `sender` (object)

Output parameters:

- `no_autonomous_outbound` (boolean)
- `ok` (boolean)
- `public_name` (string)
- `review_required_before_send` (boolean)
- `tool` (string)

### `growthos_owner_facing_report` (~135 tokens)

GrowthOS Owner-Facing Report

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.

Input parameters:

- `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.
- `prospect` (object, required)
- `sender` (object)

Output parameters:

- `no_autonomous_outbound` (boolean)
- `ok` (boolean)
- `public_name` (string)
- `review_required_before_send` (boolean)
- `tool` (string)

### `growthos_opportunity_scout_packet` (~62 tokens)

GrowthOS Opportunity Scout Packet

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

Input parameters:

- `opportunity` (object, required): Opportunity input. opportunity_type must be one of the registered Opportunity Scout types.

Output parameters:

- `no_autonomous_outbound` (boolean)
- `ok` (boolean)
- `public_name` (string)
- `review_required_before_send` (boolean)
- `tool` (string)

### `growthos_digital_clone_packet` (~117 tokens)

GrowthOS Digital Clone Packet

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.

Input parameters:

- `perspective_context` (string): Optional buyer pain or delivery context to ground through stackfast.perspective.translate.
- `prospect` (object, required): 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.

Output parameters:

- `no_autonomous_outbound` (boolean)
- `ok` (boolean)
- `public_name` (string)
- `review_required_before_send` (boolean)
- `tool` (string)

### `estimator_catalog_search` (~153 tokens)

OCE Estimator catalog search

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

Input parameters:

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

Output parameters:

- `no_accounting_write` (boolean)
- `ok` (boolean)
- `product` (string)
- `review_required_before_customer_release` (boolean)
- `tool` (string)

### `estimator_catalog_sources` (~153 tokens)

OCE Estimator catalog sources

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

Input parameters:

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

Output parameters:

- `no_accounting_write` (boolean)
- `ok` (boolean)
- `product` (string)
- `review_required_before_customer_release` (boolean)
- `tool` (string)

### `estimator_estimate_create_draft` (~150 tokens)

OCE Estimator estimate create draft

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

Input parameters:

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

Output parameters:

- `no_accounting_write` (boolean)
- `ok` (boolean)
- `product` (string)
- `review_required_before_customer_release` (boolean)
- `tool` (string)

### `estimator_estimate_add_line` (~149 tokens)

OCE Estimator estimate add line

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

Input parameters:

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

Output parameters:

- `no_accounting_write` (boolean)
- `ok` (boolean)
- `product` (string)
- `review_required_before_customer_release` (boolean)
- `tool` (string)

### `estimator_estimate_update_line` (~149 tokens)

OCE Estimator estimate update line

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

Input parameters:

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

Output parameters:

- `no_accounting_write` (boolean)
- `ok` (boolean)
- `product` (string)
- `review_required_before_customer_release` (boolean)
- `tool` (string)

### `estimator_estimate_convert_to_bid` (~150 tokens)

OCE Estimator estimate convert to bid

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

Input parameters:

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

Output parameters:

- `no_accounting_write` (boolean)
- `ok` (boolean)
- `product` (string)
- `review_required_before_customer_release` (boolean)
- `tool` (string)

### `estimator_estimate_convert_to_invoice` (~151 tokens)

OCE Estimator estimate convert to invoice

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

Input parameters:

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

Output parameters:

- `no_accounting_write` (boolean)
- `ok` (boolean)
- `product` (string)
- `review_required_before_customer_release` (boolean)
- `tool` (string)

### `estimator_estimate_progress_invoice` (~150 tokens)

OCE Estimator estimate progress invoice

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

Input parameters:

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

Output parameters:

- `no_accounting_write` (boolean)
- `ok` (boolean)
- `product` (string)
- `review_required_before_customer_release` (boolean)
- `tool` (string)

### `estimator_estimate_export` (~148 tokens)

OCE Estimator estimate export

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

Input parameters:

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

Output parameters:

- `no_accounting_write` (boolean)
- `ok` (boolean)
- `product` (string)
- `review_required_before_customer_release` (boolean)
- `tool` (string)

### `estimator_policy_check` (~147 tokens)

OCE Estimator policy check

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

Input parameters:

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

Output parameters:

- `no_accounting_write` (boolean)
- `ok` (boolean)
- `product` (string)
- `review_required_before_customer_release` (boolean)
- `tool` (string)

### `estimator_receipt_get` (~148 tokens)

OCE Estimator receipt get

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

Input parameters:

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

Output parameters:

- `no_accounting_write` (boolean)
- `ok` (boolean)
- `product` (string)
- `review_required_before_customer_release` (boolean)
- `tool` (string)

### `ai_receptionist_status` (~63 tokens)

AI Receptionist Status

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.

Input parameters:

- `call_id` (string, required)
- `tenant_id` (string)

Output parameters:

- `live_line_touched` (boolean)
- `no_autonomous_outbound` (boolean)
- `ok` (boolean)
- `public_name` (string)
- `tool` (string)

### `ai_receptionist_review_queue` (~61 tokens)

AI Receptionist Review Queue

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.

Input parameters:

- `limit` (integer)
- `tenant_id` (string)

Output parameters:

- `live_line_touched` (boolean)
- `no_autonomous_outbound` (boolean)
- `ok` (boolean)
- `public_name` (string)
- `tool` (string)

### `ai_receptionist_callback_packet` (~62 tokens)

AI Receptionist Callback Packet

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.

Input parameters:

- `call_id` (string, required)
- `tenant_id` (string)

Output parameters:

- `live_line_touched` (boolean)
- `no_autonomous_outbound` (boolean)
- `ok` (boolean)
- `public_name` (string)
- `tool` (string)

### `talent_scout_my_profile_upsert` (~510 tokens)

Talent Scout Profile Setup Upsert

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.

Input parameters:

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

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_profile_upsert` (~509 tokens)

Talent Scout Profile Setup Upsert

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.

Input parameters:

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

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_my_profile_status` (~207 tokens)

Talent Scout My Profile Status

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.

Input parameters:

- `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.
- `sqlite_path` (string): Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
- `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.
- `tenant_id` (string)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_profile_status` (~206 tokens)

Talent Scout My Profile Status

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.

Input parameters:

- `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.
- `sqlite_path` (string): Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
- `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.
- `tenant_id` (string)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_reconcile_application_history` (~254 tokens)

Talent Scout Reconcile Application History

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.

Input parameters:

- `auth_token_key` (string): Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
- `corrections` (array, required)
- `database_url_key` (string): Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
- `dry_run` (boolean): Preview matched history records and the redacted reconciliation receipt without writing.
- `if_match_updated_at` (string, required): The exact profile_version_updated_at from applicant_profile_status. A stale value is rejected.
- `sqlite_path` (string): Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
- `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.
- `tenant_id` (string, required)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_set_search_rails` (~302 tokens)

Talent Scout Set Search Rails

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.

Input parameters:

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

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_upsert_campaign_profile` (~434 tokens)

Talent Scout Upsert Campaign Profile

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.

Input parameters:

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

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_discover_companies_by_campaign` (~334 tokens)

Talent Scout Discover Companies By Campaign

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.

Input parameters:

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

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_discover_local_companies` (~368 tokens)

Talent Scout Discover Local Companies

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.

Input parameters:

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

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_scan_company_for_roles` (~399 tokens)

Talent Scout Scan Company For Roles

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.

Input parameters:

- `allow_live_firecrawl` (boolean): Backward-compatible no-op for this scanner; official ATS/API scans are preferred when available.
- `auth_token_key` (string): Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
- `campaign_id` (string)
- `careers_url` (string)
- `company_domain` (string): Backward-compatible alias for company_homepage_url; bare domains are normalized to https://<domain>.
- `company_homepage_url` (string)
- `company_name` (string)
- `company_target_id` (string)
- `database_url_key` (string): Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
- `eligible_countries` (array)
- `limit` (integer)
- `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.
- `source_url` (string)
- `sqlite_path` (string): Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
- `target_lanes` (array)
- `target_role_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.
- `tenant_id` (string)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_person_research_notes` (~220 tokens)

Talent Scout Find Company Contacts

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.

Input parameters:

- `auth_token_key` (string): Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
- `campaign_id` (string)
- `company_name` (string)
- `company_target_id` (string)
- `database_url_key` (string): Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
- `limit` (integer)
- `role_lane` (string)
- `sqlite_path` (string): Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
- `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.
- `tenant_id` (string)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_business_email_receipt` (~228 tokens)

Talent Scout Enrich Contact Email

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.

Input parameters:

- `auth_token_key` (string): Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
- `company_name` (string)
- `company_target_id` (string)
- `database_url_key` (string): Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
- `domain` (string)
- `first_name` (string)
- `last_name` (string)
- `person_label` (string)
- `person_name` (string)
- `sqlite_path` (string): Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
- `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.
- `tenant_id` (string)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_draft_manual_note` (~288 tokens)

Talent Scout Draft Manual Note

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.

Input parameters:

- `application_id` (string)
- `apply` (boolean)
- `auth_token_key` (string): Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
- `campaign_id` (string)
- `channel` (string)
- `company` (string)
- `company_name` (string)
- `company_target_id` (string)
- `contact_name` (string)
- `database_url_key` (string): Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
- `goal` (string)
- `person_label` (string)
- `person_name` (string)
- `queue_item_id` (string)
- `send` (boolean)
- `sqlite_path` (string): Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
- `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.
- `tenant_id` (string)
- `title` (string)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_record_manual_note` (~334 tokens)

Talent Scout Record Manual Note Receipt

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.

Input parameters:

- `apply` (boolean)
- `auth_token_key` (string): Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
- `campaign_id` (string)
- `channel` (string)
- `company_name` (string)
- `company_target_id` (string)
- `database_url_key` (string): Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
- `decision` (string, required): Human decision to record. No option sends anything automatically.
- `draft_text` (string)
- `edited_draft_text` (string)
- `goal` (string)
- `manual_note_id` (string, required)
- `notes` (string)
- `person_label` (string)
- `person_name` (string)
- `send` (boolean)
- `sent_text` (string): Exact text the human actually sent manually. Talent Scout stores this receipt but never sends it.
- `sqlite_path` (string): Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
- `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.
- `tenant_id` (string)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_record_relationship_activity` (~331 tokens)

Talent Scout Record Relationship Activity

Record one human-reported email, LinkedIn, 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.

Input parameters:

- `artifact_url` (string): Optional governed evidence URL; no artifact body is copied.
- `auth_token_key` (string): Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
- `channel` (string, required)
- `company` (string, required)
- `contact_name` (string, required)
- `database_url_key` (string): Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
- `idempotency_key` (string, required): Caller-stable key that makes retries return the original immutable receipt.
- `next_touch_at` (string): Optional ISO-8601 follow-up time.
- `occurred_at` (string, required): ISO-8601 timestamp for the human-completed activity.
- `related_application_id` (string)
- `related_queue_item_id` (string)
- `sqlite_path` (string): Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
- `summary` (string, required): Concise factual summary of the already-completed human activity.
- `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.
- `tenant_id` (string, required)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_record_application` (~147 tokens)

Talent Scout Record Application

Record that the human manually submitted an application for a Talent Scout queue item. This updates Talent Scout lifecycle status, schedules follow-up tasks, and records a submission receipt only; it never applies, sends, clicks, or submits anything automatically.

Input parameters:

- `actor_id` (string): Optional actor label for the manual receipt.
- `apply` (boolean)
- `notes` (string): Optional human note stored in the receipt response only.
- `queue_item_id` (string): Talent Scout queue item that Robert manually submitted.
- `send` (boolean)
- `submitted_at` (string): Optional ISO timestamp for the manual submission. Defaults to now.
- `tenant_id` (string)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_form_schema_receipt` (~86 tokens)

Talent Scout Form Schema Receipt

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.

Input parameters:

- `apply` (boolean)
- `fields` (array, required)
- `send` (boolean)
- `submit` (boolean)
- `tenant_id` (string)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_browser_fill_receipt` (~120 tokens)

Talent Scout Browser Fill Receipt

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.

Input parameters:

- `apply` (boolean)
- `fields` (array)
- `profile_values` (object)
- `readbacks` (object)
- `schema_receipt` (object)
- `send` (boolean)
- `submit` (boolean)
- `tenant_id` (string)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_record_queue_decision` (~223 tokens)

Talent Scout Record Opportunity Decision

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.

Input parameters:

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

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_import_byoc_delta` (~132 tokens)

Talent Scout Import BYOC Delta

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.

Input parameters:

- `apply` (boolean)
- `contacts` (array)
- `delta` (object)
- `direction` (string)
- `idempotency_key` (string)
- `packets` (array)
- `queue_sync_version` (string)
- `roles` (array)
- `send` (boolean)
- `source` (string)
- `tenant_id` (string)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_pipeline_describe` (~47 tokens)

Talent Scout Pipeline Describe

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

Input parameters:

- `tenant_id` (string)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_search_opportunities` (~193 tokens)

Talent Scout Search Opportunities

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.

Input parameters:

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

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_role_review` (~129 tokens)

Talent Scout Role Review

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.

Input parameters:

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

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_score_fit` (~129 tokens)

Talent Scout Role Review

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.

Input parameters:

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

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_explain_preferences_match` (~114 tokens)

Talent Scout Preferences Match Explainer

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.

Input parameters:

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

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_create_packet` (~83 tokens)

Talent Scout Create Packet

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

Input parameters:

- `actor_id` (string)
- `notes` (string)
- `opportunity_mode` (string)
- `output_kind` (string)
- `queue_item_id` (string, required)
- `tenant_id` (string)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_compose_application` (~590 tokens)

Talent Scout Compose Application

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.

Input parameters:

- `actor_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.
- `baseline_resume_text` (string): Optional private owner evidence override. Used only to map JD requirements to proof points; never returned raw.
- `canonical_job_id` (string): Optional canonical job id lookup. Resolves only to an existing Talent Scout queue/history record.
- `careers_url` (string): Official careers page URL when known. Helps distinguish a real posting from a generic board/root page.
- `company` (string): Optional lookup key. Use with title when queue_item_id is not known; exact normalized match is required.
- `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.
- `compare_providers` (boolean): When true, run bounded OpenAI/Gemma/Gemini comparison receipts without exposing alternate raw drafts.
- `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.
- `notes` (string)
- `output_kind` (string)
- `owner_profile_text` (string): Optional private owner evidence from a resume/profile setup interview. Used for proof mapping; never returned raw.
- `portal_application_id` (string): Alias for application_id when the id came from an external portal.
- `queue_item_id` (string)
- `requisition_id` (string): Alias for application_id when the id is a req/requisition id.
- `tenant_id` (string)
- `title` (string): Optional lookup key. Use with company when queue_item_id is not known; exact normalized match is required.
- `user_supplied_jd_text` (string): Alias for job_description_text; treated as authoritative user-supplied JD evidence after auto-hydration fails.
- `voice_anchor` (string)
- `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.

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_draft_outreach` (~102 tokens)

Talent Scout Draft Manual Note

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.

Input parameters:

- `apply` (boolean)
- `artifact_type` (string)
- `pains` (array, required)
- `send` (boolean)
- `target_name` (string, required)
- `tenant_id` (string)
- `voice_profile` (string)
- `voice_samples` (array)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_review_queue` (~399 tokens)

Talent Scout Review Queue

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.

Input parameters:

- `compact` (boolean): Return compact queue metadata and a daily_pipeline_summary instead of heavy control-tower sections.
- `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_detail` (boolean): When true, include full queue item payloads. Defaults false so hosted MCP review_queue stays small and fast.
- `include_items` (boolean): When false, return health/counts/timing only without loading queue item payloads. Use for fast connector smoke tests.
- `include_sync_delta` (boolean): When true, include a guarded scout.import_delta-compatible cloud-to-BYOC queue sync payload. Defaults false.
- `limit` (integer)
- `owner_profile` (object): Optional owner preference context used to refresh stale zero-score queue items inside this tenant only.
- `profile` (object): Alias for owner_profile when reviewing stale queue items.
- `run_id` (string)
- `status` (string)
- `tenant_id` (string)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_daily_pipeline` (~348 tokens)

Talent Scout Daily Pipeline

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.

Input parameters:

- `compact` (boolean): Return counts, status buckets, mailbox status, and a bounded slate without full bucket payloads. Defaults true for hosted MCP latency.
- `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.
- `include_items` (boolean): Return top-level queue cards. Defaults false so compact daily reads return the bounded operating summary only.
- `limit` (integer)
- `owner_profile` (object): Optional owner preference context used to refresh stale zero-score queue items inside this tenant only.
- `profile` (object): Alias for owner_profile when reviewing stale queue items.
- `section_limit` (integer)
- `slate_limit` (integer)
- `tenant_id` (string)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_mail_signals` (~101 tokens)

Talent Scout Mail Signals

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.

Input parameters:

- `limit` (integer)
- `tenant_id` (string)

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `talent_scout_application_workup` (~316 tokens)

Talent Scout Application Workup

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.

Input parameters:

- `application_id` (string): Optional ATS/portal application or requisition id, such as R110984. Resolves only to an existing Talent Scout queue/history record.
- `canonical_job_id` (string): Optional canonical job id lookup. Resolves only to an existing Talent Scout queue/history record.
- `company` (string): Company name lookup when queue_item_id is not known.
- `include_follow_up_plan` (boolean)
- `include_interview_prep` (boolean)
- `notes` (string)
- `portal_application_id` (string): Alias for application_id when the id came from an external portal.
- `queue_item_id` (string): Preferred exact Talent Scout queue item id. If omitted, provide company and title.
- `requisition_id` (string): Alias for application_id when the id is a req/requisition id.
- `tenant_id` (string)
- `title` (string): Role title lookup when queue_item_id is not known.

Output parameters:

- `drafts_never_sends` (boolean)
- `no_autonomous_outbound` (boolean)
- `public_tool` (string)
- `result` (object)

### `voice_intelligence_run` (~429 tokens)

Voice Intelligence Run

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.

Input parameters:

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

Output parameters:

- `actual_script` (object)
- `authority_report` (object)
- `input_kind` (string)
- `llm` (object|null)
- `receipts` (array)
- `schema_version` (string)
- `summary` (object)
- `transcript` (string)
- `transcript_source` (string)

### `search` (~42 tokens)

Search StackFast Brain

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

Input parameters:

- `query` (string, required): Natural language search query.

Output parameters:

- `results` (array)

### `fetch` (~194 tokens)

Fetch StackFast Brain Result

Fetch a StackFast Brain search result 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 }); continue with next_page until complete is true.

Input parameters:

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

Output parameters:

- `complete` (boolean)
- `content_sha256` (string)
- `error_code` (string)
- `id` (string)
- `message` (string)
- `metadata` (object)
- `next_page` (integer|null)
- `ok` (boolean)
- `page` (integer)
- `page_end` (integer)
- `page_sha256` (string)
- `page_size` (integer)
- `page_start` (integer)
- `supported_call_shapes` (array)
- `text` (string)
- `title` (string)
- `total_chars` (integer)
- `total_pages` (integer)
- `url` (string)

### `boot_status` (~22 tokens)

Boot Status

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

Output parameters:

- `auth` (object)
- `canonical_url` (string)
- `generated_at` (string)
- `ok` (boolean)
- `schema_version` (string)
- `service` (string)
- `tools` (object)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/trupe-rs-expert-brain/api-mcp#diagnostics

## Score history

- 2026-08-03: 74
- 2026-08-02: 74
- 2026-08-01: 73
- 2026-07-31: 73
- 2026-07-30: 65
- 2026-07-29: 67
- 2026-07-28: 67
- 2026-07-27: 66
- 2026-07-26: 65

## Links

- Remote endpoint: https://stackfast.ai/api/mcp
- Repository: https://github.com/stackfast-technologies/mcp-brain-server
- Changelog RSS feed: https://verifymcp.io/servers/trupe-rs-expert-brain/api-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/trupe-rs-expert-brain/api-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/trupe-rs-expert-brain/api-mcp