StackFast FractWin Expert Brain
by Trupe-Rs · remote · no sign-in to list tools · v1.0.0 · published by GitHub user Trupe-Rs
Expert knowledge base for sales, negotiation, strategy, operations, and risk.
74 tools: 2 do something that can't be undone, 45 change things and 27 only read.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone2Claude Code: ask: see these tools
- Changes things45Claude Code: ask: see these tools
- Only reads27Claude Code: allow: see these tools
48 checks matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http expert-brain https://stackfast.ai/api/mcpFindings
Matches of fixed checks, with the text they matched.
The server marks "artifact_generate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true}; The name "artifact_generate" says "generate": a word for a change.
- Warnartifact_save
The server marks "artifact_save" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true}; The name "artifact_save" says "save": a word for a change.
- Warnartifact_export
The server marks "artifact_export" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true}; The description's first verb is "create": a word for a change.
- Warnreply_compose
The server marks "reply_compose" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true}; The name "reply_compose" says "reply": a word for sending, and what is sent cannot be taken back.
The server marks "growthos_business_brain_interview" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "start": a word for a change.
The server marks "growthos_revenue_capture_packet" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "growthos_revenue_capture_packet" says "capture": a word that usually means money moves, which cannot be taken back.
Show 42 more findingsShow fewer
The server marks "cogentcast_package_create" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "cogentcast_package_create" says "create": a word for a change.
The server marks "cogentcast_production_run" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "cogentcast_production_run" says "run": a word for a change.
The server marks "estimator_estimate_create_draft" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "estimator_estimate_create_draft" says "create": a word for a change.
The server marks "estimator_estimate_add_line" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "estimator_estimate_add_line" says "add": a word for a change.
The server marks "estimator_estimate_update_line" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "estimator_estimate_update_line" says "update": a word for a change.
The server marks "estimator_estimate_convert_to_bid" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "estimator_estimate_convert_to_bid" says "convert": a word for a change.
The server marks "estimator_estimate_convert_to_invoice" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "estimator_estimate_convert_to_invoice" says "convert": a word for a change.
The server marks "talent_scout_my_profile_upsert" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "talent_scout_my_profile_upsert" says "upsert": a word for a change.
The server marks "talent_scout_profile_upsert" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "talent_scout_profile_upsert" says "upsert": a word for a change.
The server marks "talent_scout_set_search_rails" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "talent_scout_set_search_rails" says "set": a word for a change.
The server marks "talent_scout_upsert_campaign_profile" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "talent_scout_upsert_campaign_profile" says "upsert": a word for a change.
The server marks "talent_scout_person_research_notes" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "generate": a word for a change.
The server marks "talent_scout_browser_fill_receipt" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "talent_scout_browser_fill_receipt" says "fill": a word for a change.
The server marks "talent_scout_import_byoc_delta" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "talent_scout_import_byoc_delta" says "import": a word for a change.
The server marks "talent_scout_search_opportunities" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "talent_scout_search_opportunities" says "search": a word for reading.
The server marks "talent_scout_create_packet" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "talent_scout_create_packet" says "create": a word for a change.
The server marks "talent_scout_generate_finished_resume" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "talent_scout_generate_finished_resume" says "generate": a word for a change.
The server marks "voice_intelligence_run" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "voice_intelligence_run" says "run": a word for a change.
The title mentions "Credential".
What this check looks forMatched text
title: "Credential Inventory"
The description mentions "credential".
What this check looks forMatched text
description: "Discover wallet-resolved credential service names and accepted aliases with..."
The description mentions "credential".
What this check looks forMatched text
description: "...terms, performs an assessment, grants a credential, or exposes protected method bodies."
The description mentions "credentials".
What this check looks forMatched text
description: "...authority, publish publicly, or expose credentials."
The description mentions "credentials".
What this check looks forMatched text
description: "...authority, publish publicly, or expose credentials."
The description mentions "credentials".
What this check looks forMatched text
description: "...authority, publish publicly, or expose credentials."
The description mentions "credentials".
What this check looks forMatched text
description: "...authority, publish publicly, or expose credentials."
The description mentions "credentials".
What this check looks forMatched text
description: "...authority, publish publicly, or expose credentials."
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
Tools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
74 tools
Can't be undone 2Claude Code: ask
growthos_revenue_capture_packetReturn a GrowthOS revenue-capture packet: scorecard, review-gated contact drafts, CogentCast site-review receipt composition, and summary for supplied local-business evidence.1 finding
Why it is in this group
- The name "growthos_revenue_capture_packet" says "capture": a word that usually means money moves, which cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "growthos_revenue_capture_packet" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "growthos_revenue_capture_packet" says "capture": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
reply_composeCompose a relationship-safe correspondence decision packet with do_not_say, safe_phrasing, channel constraints, manual approval, and a correspondence_response artifact audit trail.1 finding
Why it is in this group
- The name "reply_compose" says "reply": a word for sending, and what is sent cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "reply_compose" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true}; The name "reply_compose" says "reply": a word for sending, and what is sent cannot be taken back.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
Changes things 45Claude Code: ask
artifact_exportCreate an audited export receipt for an approved artifact or internal draft.1 finding
Why it is in this group
- The description's first verb is "create": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "artifact_export" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true}; The description's first verb is "create": a word for a change.
Description, as the server wrote it Create an audited export receipt for an approved artifact or internal draft. External publish remains separate and human-approved.
Annotations the server declares
- readOnlyHint: true
artifact_generateGenerate a governed, tenant-scoped artifact draft with no-fabrication placeholders, analyzer provenance, MASK, brand status, and approval requirements.1 finding
Why it is in this group
- The name "artifact_generate" says "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "artifact_generate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true}; The name "artifact_generate" says "generate": a word for a change.
Description, as the server wrote it Generate a governed, tenant-scoped artifact draft with no-fabrication placeholders, analyzer provenance, MASK, brand status, and approval requirements.
Annotations the server declares
- readOnlyHint: true
artifact_refineRefine an existing artifact draft while preserving tenant boundary, provenance, MASK status, and approval posture.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Refine an existing artifact draft while preserving tenant boundary, provenance, MASK status, and approval posture.
Annotations the server declares
- readOnlyHint: true
artifact_saveApprove/save an artifact and mark tenant-scoped learning-loop eligibility.1 finding
Why it is in this group
- The name "artifact_save" says "save": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "artifact_save" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true}; The name "artifact_save" says "save": a word for a change.
Description, as the server wrote it Approve/save an artifact and mark tenant-scoped learning-loop eligibility. Does not publish externally.
Annotations the server declares
- readOnlyHint: true
cogentcast_package_createCreate 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 thr…2 findings
Why it is in this group
- The name "cogentcast_package_create" says "create": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...authority, publish publicly, or expose credentials."
- Warn
The server marks "cogentcast_package_create" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "cogentcast_package_create" says "create": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
cogentcast_production_runRequest one leased production stage.2 findings
Why it is in this group
- The name "cogentcast_production_run" says "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...authority, publish publicly, or expose credentials."
- Warn
The server marks "cogentcast_production_run" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "cogentcast_production_run" says "run": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
- idempotentHint: true
credentials_inventoryDiscover wallet-resolved credential service names and accepted aliases without exposing secret values.2 findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The title mentions "Credential".
What this check looks forMatched text
title: "Credential Inventory"
- Info
The description mentions "credential".
What this check looks forMatched text
description: "Discover wallet-resolved credential service names and accepted aliases with..."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
dealership_check_lead_follow_upDealership OS checks a tenant-scoped lead against consent, STOP, quiet-hours, pacing, verified-sender, identity, assignment, and manager-exception rules.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
dealership_sales_floor_briefDealership OS returns a public-safe, tenant-scoped coaching brief for opportunity leak diagnosis, ownership and next actions, daily manager reconciliation, customer connection, cus…1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...terms, performs an assessment, grants a credential, or exposes protected method bodies."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
estimator_catalog_sourcesOperate on tenant-scoped OCE Estimator/Appraiser catalog sources/items, including the StackFast storefront catalog, through the generic estimator_* control-plane contract.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Operate on tenant-scoped OCE Estimator/Appraiser catalog sources/items, including the StackFast storefront catalog, through the generic estimator_* control-plane contract.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
estimator_estimate_add_lineOperate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.1 finding
Why it is in this group
- The name "estimator_estimate_add_line" says "add": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "estimator_estimate_add_line" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "estimator_estimate_add_line" says "add": a word for a change.
Description, as the server wrote it Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
estimator_estimate_convert_to_bidOperate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.1 finding
Why it is in this group
- The name "estimator_estimate_convert_to_bid" says "convert": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "estimator_estimate_convert_to_bid" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "estimator_estimate_convert_to_bid" says "convert": a word for a change.
Description, as the server wrote it Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
estimator_estimate_convert_to_invoicePrepare an OCE Estimator/Appraiser document or QBO handoff contract.1 finding
Why it is in this group
- The name "estimator_estimate_convert_to_invoice" says "convert": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "estimator_estimate_convert_to_invoice" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "estimator_estimate_convert_to_invoice" says "convert": a word for a change.
Description, as the server wrote it Prepare an OCE Estimator/Appraiser document or QBO handoff contract. Review-gated; does not write to accounting systems.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
estimator_estimate_create_draftOperate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.1 finding
Why it is in this group
- The name "estimator_estimate_create_draft" says "create": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "estimator_estimate_create_draft" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "estimator_estimate_create_draft" says "create": a word for a change.
Description, as the server wrote it Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
estimator_estimate_exportOperate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
estimator_estimate_progress_invoicePrepare an OCE Estimator/Appraiser document or QBO handoff contract.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Prepare an OCE Estimator/Appraiser document or QBO handoff contract. Review-gated; does not write to accounting systems.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
estimator_estimate_update_lineOperate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.1 finding
Why it is in this group
- The name "estimator_estimate_update_line" says "update": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "estimator_estimate_update_line" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "estimator_estimate_update_line" says "update": a word for a change.
Description, as the server wrote it Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
estimator_policy_checkOperate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
growthos_business_brain_interviewStart or append a GrowthOS Business Brain Interview using the existing interview/session model.1 finding
Why it is in this group
- The description's first verb is "start": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "growthos_business_brain_interview" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "start": a word for a change.
Description, as the server wrote it Start or append a GrowthOS Business Brain Interview using the existing interview/session model. Outputs remain draft_review_required before automation.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
growthos_digital_clone_packetBuild a draft GrowthOS digital-clone render packet from normalized signals, evidence, runtime tenant voice profile, and PERSPECTIVE capability grounding.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
growthos_opportunity_scout_packetBuild an Opportunity Scout packet for customer, talent, contract, or capital opportunities using the existing gate-first policy layer and no new persistence table.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Build an Opportunity Scout packet for customer, talent, contract, or capital opportunities using the existing gate-first policy layer and no new persistence table.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
growthos_owner_facing_reportRender 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 findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
growthos_scorecardBuild a private GrowthOS Revenue Capture Scorecard from supplied public business signals.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
talent_scout_application_workupBuild 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 …No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
talent_scout_browser_fill_receiptBuild or verify a keyboard-event ATS fill plan from a complete form schema.1 finding
Why it is in this group
- The name "talent_scout_browser_fill_receipt" says "fill": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "talent_scout_browser_fill_receipt" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "talent_scout_browser_fill_receipt" says "fill": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
talent_scout_business_email_receiptPrepare Hunter.io-style business email enrichment receipts for a qualified contact.1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
talent_scout_compose_applicationCompose a draft-only first-party job-seeker application artifact for the account owner from a real Talent Scout queue item using JD evidence.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
talent_scout_correct_relationship_activityAppend an immutable correction for the channel and direction of an existing Talent Scout Relationship Core receipt.1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
talent_scout_create_packetCreate a draft-only application or opportunity packet from an existing Talent Scout queue item.1 finding
Why it is in this group
- The name "talent_scout_create_packet" says "create": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "talent_scout_create_packet" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "talent_scout_create_packet" says "create": a word for a change.
Description, as the server wrote it Create a draft-only application or opportunity packet from an existing Talent Scout queue item. Human approval is required before external use.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
talent_scout_draft_outreachDraft a human-reviewed manual note from safe pains and voice evidence.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
talent_scout_form_schema_receiptEnumerate every required and optional ATS form field before any fill attempt.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
talent_scout_generate_finished_resumeGenerate 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 …1 finding
Why it is in this group
- The name "talent_scout_generate_finished_resume" says "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "talent_scout_generate_finished_resume" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "talent_scout_generate_finished_resume" says "generate": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
talent_scout_import_byoc_deltaImport a guarded BYOC-local Talent Scout queue delta into the cloud queue.1 finding
Why it is in this group
- The name "talent_scout_import_byoc_delta" says "import": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "talent_scout_import_byoc_delta" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "talent_scout_import_byoc_delta" says "import": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
talent_scout_my_profile_upsertCreate 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…2 findings
Why it is in this group
- The name "talent_scout_my_profile_upsert" says "upsert": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
- Warn
The server marks "talent_scout_my_profile_upsert" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "talent_scout_my_profile_upsert" says "upsert": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
talent_scout_person_research_notesGenerate public contact-research labels and safe LinkedIn search queries so the account owner can decide who to review manually.2 findings
Why it is in this group
- The description's first verb is "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
- Warn
The server marks "talent_scout_person_research_notes" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "generate": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
talent_scout_profile_upsertCreate 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…2 findings
Why it is in this group
- The name "talent_scout_profile_upsert" says "upsert": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
- Warn
The server marks "talent_scout_profile_upsert" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "talent_scout_profile_upsert" says "upsert": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
talent_scout_reconcile_application_historyCorrect an owner-reported application-history state with optimistic concurrency and an append-only reconciliation receipt.1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
talent_scout_record_applicationRecord that the human manually submitted an application.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
talent_scout_record_manual_noteRecord a human decision and receipt on a Talent Scout manual-note draft.1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
talent_scout_record_queue_decisionRecord the account owner's manual decision on an existing Talent Scout queue item: keep, top priority, hold/revisit, pass, or not-a-fit.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
talent_scout_record_relationship_activityRecord one human-reported email, LinkedIn, SMS, call, or visit in the existing StackFast Relationship Core.1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
talent_scout_search_opportunitiesRun fresh governed public-opportunity discovery for the account owner to find roles they may review and apply to manually.1 finding
Why it is in this group
- The name "talent_scout_search_opportunities" says "search": a word for reading.
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "talent_scout_search_opportunities" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "talent_scout_search_opportunities" says "search": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
talent_scout_set_search_railsPersist the active Talent Scout search strategy for a tenant: target lanes, compensation floor, geography, positive/negative filters, resume-variant priority, travel posture, and v…2 findings
Why it is in this group
- The name "talent_scout_set_search_rails" says "set": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
- Warn
The server marks "talent_scout_set_search_rails" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "talent_scout_set_search_rails" says "set": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
talent_scout_upsert_campaign_profileCreate, update, activate, pause, or archive a saved Talent Scout direct-company discovery campaign.2 findings
Why it is in this group
- The name "talent_scout_upsert_campaign_profile" says "upsert": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
- Warn
The server marks "talent_scout_upsert_campaign_profile" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "talent_scout_upsert_campaign_profile" says "upsert": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
voice_intelligence_runRun 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…1 finding
Why it is in this group
- The name "voice_intelligence_run" says "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "voice_intelligence_run" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "voice_intelligence_run" says "run": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
- idempotentHint: false
Only reads 27Claude Code: allow
ai_receptionist_callback_packetReturn a human-review callback packet for one AI Receptionist call.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
ai_receptionist_review_queueList recent AI Receptionist call-loop receipts for human review, including callback and A2P-gated inbound SMS status where present.No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
ai_receptionist_statusRead the Desk ticket, CRM callback task, call-link receipt, and A2P-gated inbound SMS posture for one AI Receptionist call ID.No findings
Why it is in this group
- The name "ai_receptionist_status" says "status": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
artifact_auditRead provenance, analyzer findings, gate status, approval state, usage, and export receipts for one tenant-scoped artifact.No findings
Why it is in this group
- The description's first verb is "read": a word for reading.
Description, as the server wrote it Read provenance, analyzer findings, gate status, approval state, usage, and export receipts for one tenant-scoped artifact.
Annotations the server declares
- readOnlyHint: true
audit_statusRead AI Stack Audit project state, deliverable refs, credit ledger, and Desk/CRM links.No findings
Why it is in this group
- The name "audit_status" says "status": a word for reading.
Description, as the server wrote it Read AI Stack Audit project state, deliverable refs, credit ledger, and Desk/CRM links.
Annotations the server declares
- readOnlyHint: true
boot_statusRead-only StackFast connector health/status check.No findings
Why it is in this group
- The name "boot_status" says "status": a word for reading.
Description, as the server wrote it Read-only StackFast connector health/status check. Does not expose secrets.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
cogentcast_approval_resolveRead and validate a server-recorded, human-authenticated approval receipt by id.1 finding
Why it is in this group
- The name "cogentcast_approval_resolve" says "resolve": a word for reading.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...authority, publish publicly, or expose credentials."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
cogentcast_package_previewValidate a Work Sample, content_type=narration_review, or content_type=audiobook_production configuration without creating state or vendor cost.1 finding
Why it is in this group
- The name "cogentcast_package_preview" says "preview": a word for reading.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...authority, publish publicly, or expose credentials."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
cogentcast_production_statusRead tenant-scoped Work Sample, narration-review, or audiobook-production state; exact hashes; current-vs-historical derivative projection; and Chief Editor/Gemini/ear/paid/publica…1 finding
Why it is in this group
- The name "cogentcast_production_status" says "status": a word for reading.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...authority, publish publicly, or expose credentials."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
estimator_catalog_searchOperate on tenant-scoped OCE Estimator/Appraiser catalog sources/items, including the StackFast storefront catalog, through the generic estimator_* control-plane contract.No findings
Why it is in this group
- The name "estimator_catalog_search" says "search": a word for reading.
Description, as the server wrote it Operate on tenant-scoped OCE Estimator/Appraiser catalog sources/items, including the StackFast storefront catalog, through the generic estimator_* control-plane contract.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
estimator_receipt_getOperate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.No findings
Why it is in this group
- The name "estimator_receipt_get" says "get": a word for reading.
Description, as the server wrote it Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
fetchFetch a StackFast Brain result or an authorized immutable session artifact by id through the AI6 MCP reader plane.No findings
Why it is in this group
- The name "fetch" says "fetch": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
searchSearch StackFast Brain knowledge through the AI6 MCP reader plane; use fetch with a returned result id for full text.No findings
Why it is in this group
- The name "search" says "search": a word for reading.
Description, as the server wrote it Search StackFast Brain knowledge through the AI6 MCP reader plane; use fetch with a returned result id for full text.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
session_file_readReturn session artifact metadata and persistent URLs.No findings
Why it is in this group
- The name "session_file_read" says "read": a word for reading.
Description, as the server wrote it Return session artifact metadata and persistent URLs. V1 intentionally omits raw artifact contents.
Annotations the server declares
- readOnlyHint: true
talent_scout_daily_pipelineReturn the closed-loop Talent Scout daily operating report from the shared tenant queue: applied pipeline, mailbox reconciliation status, follow-up due, open roles, availability ch…No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
talent_scout_discover_companies_by_campaignPreview the account owner's saved business-list campaign.1 finding
Why it is in this group
- The description's first verb is "preview": a word for reading.
Findings
- Info
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
- idempotentHint: true
talent_scout_discover_local_companiesPreview the account owner's saved local business-list campaign.1 finding
Why it is in this group
- The description's first verb is "preview": a word for reading.
Findings
- Info
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
- idempotentHint: true
talent_scout_draft_manual_notePreview a manual note for Robert to copy or edit himself.1 finding
Why it is in this group
- The description's first verb is "preview": a word for reading.
Findings
- Info
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
talent_scout_explain_preferences_matchExplain in prose how an existing saved job overlaps with and differs from the account owner's stated workplace preferences.No findings
Why it is in this group
- The name "talent_scout_explain_preferences_match" says "explain": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
talent_scout_mail_signalsRead Talent Scout mail-signal status from the same server-side Gmail reconciliation path used by review_queue.No findings
Why it is in this group
- The description's first verb is "read": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
talent_scout_my_profile_statusRead 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…1 finding
Why it is in this group
- The name "talent_scout_my_profile_status" says "status": a word for reading.
Findings
- Info
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
talent_scout_pipeline_describeReturn a compact Talent Scout readiness receipt: pipeline version, surface mode, callable tool groups, and manual-review safety flags.No findings
Why it is in this group
- The name "talent_scout_pipeline_describe" says "describe": a word for reading.
Description, as the server wrote it Return a compact Talent Scout readiness receipt: pipeline version, surface mode, callable tool groups, and manual-review safety flags. Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
talent_scout_profile_statusRead 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…1 finding
Why it is in this group
- The name "talent_scout_profile_status" says "status": a word for reading.
Findings
- Info
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
talent_scout_review_queueRead 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…No findings
Why it is in this group
- The description's first verb is "read": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: false
talent_scout_role_reviewCompare 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.No findings
Why it is in this group
- The description's first verb is "compare": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
talent_scout_scan_company_for_rolesPreview a qualified company target for direct careers URLs and role-lane matches.1 finding
Why it is in this group
- The description's first verb is "preview": a word for reading.
Findings
- Info
The input schema at properties.tenant_database_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.tenant_database_type.description: "...oud only with wallet-resolved tenant DB credentials."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
- idempotentHint: true
talent_scout_score_fitCompare 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.No findings
Why it is in this group
- The description's first verb is "compare": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http expert-brain https://stackfast.ai/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__expert-brain__session_file_read",
"mcp__expert-brain__audit_status",
"mcp__expert-brain__artifact_audit",
"mcp__expert-brain__cogentcast_package_preview",
"mcp__expert-brain__cogentcast_production_status",
"mcp__expert-brain__cogentcast_approval_resolve",
"mcp__expert-brain__estimator_catalog_search",
"mcp__expert-brain__estimator_receipt_get",
"mcp__expert-brain__ai_receptionist_status",
"mcp__expert-brain__ai_receptionist_review_queue",
"mcp__expert-brain__ai_receptionist_callback_packet",
"mcp__expert-brain__talent_scout_my_profile_status",
"mcp__expert-brain__talent_scout_profile_status",
"mcp__expert-brain__talent_scout_discover_companies_by_campaign",
"mcp__expert-brain__talent_scout_discover_local_companies",
"mcp__expert-brain__talent_scout_scan_company_for_roles",
"mcp__expert-brain__talent_scout_draft_manual_note",
"mcp__expert-brain__talent_scout_pipeline_describe",
"mcp__expert-brain__talent_scout_role_review",
"mcp__expert-brain__talent_scout_score_fit",
"mcp__expert-brain__talent_scout_explain_preferences_match",
"mcp__expert-brain__talent_scout_review_queue",
"mcp__expert-brain__talent_scout_daily_pipeline",
"mcp__expert-brain__talent_scout_mail_signals",
"mcp__expert-brain__search",
"mcp__expert-brain__fetch",
"mcp__expert-brain__boot_status"
],
"ask": [
"mcp__expert-brain__credentials_inventory",
"mcp__expert-brain__dealership_check_lead_follow_up",
"mcp__expert-brain__dealership_sales_floor_brief",
"mcp__expert-brain__artifact_generate",
"mcp__expert-brain__artifact_refine",
"mcp__expert-brain__artifact_save",
"mcp__expert-brain__artifact_export",
"mcp__expert-brain__reply_compose",
"mcp__expert-brain__growthos_scorecard",
"mcp__expert-brain__growthos_business_brain_interview",
"mcp__expert-brain__growthos_revenue_capture_packet",
"mcp__expert-brain__growthos_owner_facing_report",
"mcp__expert-brain__growthos_opportunity_scout_packet",
"mcp__expert-brain__growthos_digital_clone_packet",
"mcp__expert-brain__cogentcast_package_create",
"mcp__expert-brain__cogentcast_production_run",
"mcp__expert-brain__estimator_catalog_sources",
"mcp__expert-brain__estimator_estimate_create_draft",
"mcp__expert-brain__estimator_estimate_add_line",
"mcp__expert-brain__estimator_estimate_update_line",
"mcp__expert-brain__estimator_estimate_convert_to_bid",
"mcp__expert-brain__estimator_estimate_convert_to_invoice",
"mcp__expert-brain__estimator_estimate_progress_invoice",
"mcp__expert-brain__estimator_estimate_export",
"mcp__expert-brain__estimator_policy_check",
"mcp__expert-brain__talent_scout_my_profile_upsert",
"mcp__expert-brain__talent_scout_profile_upsert",
"mcp__expert-brain__talent_scout_reconcile_application_history",
"mcp__expert-brain__talent_scout_set_search_rails",
"mcp__expert-brain__talent_scout_upsert_campaign_profile",
"mcp__expert-brain__talent_scout_person_research_notes",
"mcp__expert-brain__talent_scout_business_email_receipt",
"mcp__expert-brain__talent_scout_record_manual_note",
"mcp__expert-brain__talent_scout_record_relationship_activity",
"mcp__expert-brain__talent_scout_correct_relationship_activity",
"mcp__expert-brain__talent_scout_record_application",
"mcp__expert-brain__talent_scout_form_schema_receipt",
"mcp__expert-brain__talent_scout_browser_fill_receipt",
"mcp__expert-brain__talent_scout_record_queue_decision",
"mcp__expert-brain__talent_scout_import_byoc_delta",
"mcp__expert-brain__talent_scout_search_opportunities",
"mcp__expert-brain__talent_scout_create_packet",
"mcp__expert-brain__talent_scout_compose_application",
"mcp__expert-brain__talent_scout_draft_outreach",
"mcp__expert-brain__talent_scout_application_workup",
"mcp__expert-brain__talent_scout_generate_finished_resume",
"mcp__expert-brain__voice_intelligence_run"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as expert-brain. Review it before you use it.
