"How to run code using Claude Desktop" matching MCP tools:

• setup_instructions

  Coal — Payments for AI agents

  Print step-by-step instructions for using Coal MCP from Claude / Cursor / any MCP client. Run this FIRST if you are unsure how to authenticate or which credentials to provide.

  Connector

• get_stats

  fomox402

  Public observability snapshot for the fomox402 broker. WHAT IT DOES: returns aggregated MCP traffic + per-tool call telemetry. Read-only, no auth required, no side effects. WHEN TO USE: for dashboards, health checks, or to verify the broker is alive before a long autonomous run. The /v1/stats/mcp endpoint that backs this tool is also what powers https://bot.staccpad.fun/dashboard. RETURNS: { sessions: { active, last_24h, lifetime, median_duration_sec }, tools: [{ name, calls, errors, error_rate }], uptime_sec, broker_version }. VISIBILITY CAVEAT: only counts streamable-HTTP traffic to https://bot.staccpad.fun/mcp. Local stdio MCP clients (e.g. Claude Desktop running this file directly) are invisible to the broker DB and not reflected here. RELATED: list_agents (per-agent activity), get_me (your own stats).

  Connector

• architect.certify

  AI Design Blueprint

  Pro/Teams — second-pass adversarial certification of an architect.validate run that scored production_ready (A or B first-pass tier). ON CLIENT TIMEOUT — DO NOT RETRY THIS TOOL. **RECOVERY FIRST**: the run_id is emitted in the FIRST notifications/progress event at t=0s (BEFORE the LLM call begins). Capture it. On timeout, call `me.validation_history(run_id='<that-id>')` to fetch the persisted cert verdict; the server-side run completes independently within a 20-minute budget. This is the canonical recovery path. Use it before considering any retry. Long-running LLM call (60-180s typical; exceeds Claude Code's ~60s idle budget); MCP clients commonly close the call before the server returns. Retrying re-runs the LLM call AND burns one of your 3 cert retry-budget attempts. Mints the certified production_ready badge when both reviewers sign off; caps the run to C/emerging when the second pass surfaces a missed production_blocker. MANDATORY DOCTRINE RULE (load-bearing): the badge certifies the EXACT code that produced the validate run_id, NOT 'this codebase' in general. If you modify, fix, or iterate the code between architect.validate and architect.certify — even a single character — cert rejects with code_fingerprint_mismatch. Fixing the code voids the run. The recovery path is always: edit code → architect.validate → fresh run_id → architect.certify on the fresh run. Do NOT cert from a stale run_id after iteration; ask the user to re-validate first. WHEN TO CALL: only after architect.validate returned tier=production_ready AND the user wants the certified badge AND the code has not been touched since the validate run. NOT for tier=draft/emerging/not_applicable runs (typed rejections fire — see below). NOT idempotent across attempts: each call is one of the 3 attempts in the retry budget. BEHAVIOR: atomic one-shot single LLM call, ~60-180s server-side at high reasoning effort (small payloads finish faster; observed p99 ~250s; server-side budget is 20 min, ~5× observed max). Exceeds typical MCP-client tool-call idle budget (~60s in Claude Code), so the FIRST notifications/progress event fires at t=0 carrying the run_id. The run is atomic by contract — no in_progress lifecycle, no cancellation, no resume. Updates the persisted run's result_json (public review URL + me.validation_history(run_id=...) reflect the cert outcome). ELIGIBILITY GATE (typed rejection enum on failure): caller must own the run, tier=production_ready, less than 24h old, not already certified, within cert retry budget (max 3 attempts), no other cert call in flight for the same run_id, code fingerprint must match the validated code, AND the submitted payload must be cert-payload-complete (see Payload Completeness below — cert rejects pre-LLM with `payload_incomplete` when an imported module's surface isn't visible in the validate payload that produced this run_id). Rejection reasons (typed Literal): auth_required, paid_plan_required, run_not_found, not_run_owner, not_eligible_tier, not_agentic_component (tier=not_applicable runs), already_certified, certification_age_exceeded, retry_budget_exhausted, code_fingerprint_mismatch, code_fingerprint_missing, code_not_on_file (caller omitted `code` argument AND the 24h cert-retry hold for this run has expired or was never written. Recovery: re-run architect.certify from the same MCP session that ran architect.validate, passing the code explicitly — the server never persists code by design), payload_incomplete (submitted/validated payload imports modules whose contents aren't visible — cert refuses pre-LLM to prevent a false-precision downgrade. Recovery: re-validate with verbatim public-surface stubs for every imported module, then re-cert on the fresh run_id. Empirically validated: PR #157 iter8/iter9 cert rejections were exactly this class — code on disk was correct, the submitted payload merely omitted module visibility), cert_consensus_score_below_threshold (consensus_median<75 — consensus runs only), cert_consensus_unstable_blocker (any principle mode_stability<80% — consensus runs only), run_state_corrupt, cert_persistence_failed, cert_in_flight (a prior architect.certify call on this run_id is still running. Poll me.validation_history for the verdict; do not retry until it resolves). PAYLOAD COMPLETENESS (load-bearing for cert eligibility): the cert reviewer reads the EXACT payload that produced the validate run_id. Imported modules whose surface isn't present in the payload cause pre-LLM `payload_incomplete` refusal. Avoidance — when validating with intent to cert, bundle public-surface stubs for every imported module: `from sqlalchemy.exc import SQLAlchemyError` → include a stub class; `from app.db import models` → include a `class models:` namespace stub with the columns/methods you reference; module-level imports of `dataclass`, `Literal`, `json`, `datetime`, `timezone` MUST also be in the payload (cert correctly catches when they're omitted — code would NameError on import). 'Submit Like Production': the payload should be the code as it would actually run, not a compressed sketch. The stubs cover IMPORTED dependencies only; the certified code's own enforcement branches (approval gates, policy checks, recovery paths) must be present in full. A `# ...` placeholder reads as an ABSENT control and is graded against you, not as shorthand for one that exists. PRE-LLM REJECTION AUDIT TRAIL: when cert rejects before the LLM call (payload_incomplete, code_fingerprint_mismatch, etc.), `certification_attempts=[]` on the response — no attempt landed in the retry budget, no LLM hop occurred. The rejection envelope's `rejection_reason` + `guidance` are the actionable surface. (Audit-trail UI surfacing of pre-LLM rejections is tracked in the platform self-audit set as anomaly #5; out of scope for the cert tool itself.) INPUTS: re-send the SAME code that produced the run_id (the architect persists findings + recommendations, never code, by design — privacy-preserving). Server compares the submitted code's SHA-256 fingerprint to the stored fingerprint and rejects mismatches. Auth: Bearer <token>, Pro or Teams plan required. UK/EU data residency (Cloud Run europe-west2). Code processed transiently by OpenAI (no-training-on-API-data) and dropped; payloads JSON-escaped + delimited as inert untrusted data — prompt-injection inside code is ignored. If the cert call fails outright (provider error, persistence error), a fresh architect.certify is the recovery path; the eligibility gate enforces the 3-attempt retry budget. For long-running cert workflows the answer is to re-validate, not to make this tool stateful. OUTCOMES: certification_status ∈ {confirmed_production_ready (badge mints), downgraded_to_emerging (cert review surfaced a missed production_blocker, tier capped at C/emerging), unavailable_provider_error (LLM call failed, retry within budget)}. Cert findings + summary + attempt history surfaced on the persisted run for full inspectability.

  Connector

• upload_media

  SendIt

  FOR CLAUDE DESKTOP ONLY (with filesystem access). For Claude.ai/web: Use create_upload_session instead - it provides a browser upload link. Upload local media to cloud storage, returning a public HTTPS URL. WHEN TO USE: • Instagram, LinkedIn, Threads, X: REQUIRED for local files before calling publish_content • TikTok: NOT NEEDED - pass local path directly to publish_content SUPPORTED FORMATS: • Images: jpg, png, gif, webp (max 10MB) • Videos: mp4, mov, webm (max 100MB) Returns { url: 'https://...' } for use in publish_content mediaUrl parameter.

  Connector

• moxie.get_documentation_patterns

  Moxie Docs

  Get Moxie's summary of how THIS repository organizes and maintains documentation - where docs live relative to code and how they are kept current. Read-only; no side effects. Returns a Markdown list of pattern entries, each with a title, explanation, and source citations. Use this to decide WHERE a new doc should go before calling propose_doc_update; for the list of WHICH docs need work, use get_documentation_opportunities instead.

  Connector

• discovery_signup_verify

  Disco

  Complete Disco signup using an email verification code. Call this after discovery_signup returns {"status": "verification_required"}. The user receives a 6-digit code by email — pass it here along with the same email address used in discovery_signup. Returns an API key on success. Args: email: Email address used in the discovery_signup call. code: 6-digit verification code from the email.

  Connector

• architect.certify

  AI Design Blueprint Doctrine

  Pro/Teams — second-pass adversarial certification of an architect.validate run that scored production_ready (A or B first-pass tier). ON CLIENT TIMEOUT — DO NOT RETRY THIS TOOL. **RECOVERY FIRST**: the run_id is emitted in the FIRST notifications/progress event at t=0s (BEFORE the LLM call begins). Capture it. On timeout, call `me.validation_history(run_id='<that-id>')` to fetch the persisted cert verdict; the server-side run completes independently within a 20-minute budget. This is the canonical recovery path. Use it before considering any retry. Long-running LLM call (60-180s typical; exceeds Claude Code's ~60s idle budget); MCP clients commonly close the call before the server returns. Retrying re-runs the LLM call AND burns one of your 3 cert retry-budget attempts. Mints the certified production_ready badge when both reviewers sign off; caps the run to C/emerging when the second pass surfaces a missed production_blocker. MANDATORY DOCTRINE RULE (load-bearing): the badge certifies the EXACT code that produced the validate run_id, NOT 'this codebase' in general. If you modify, fix, or iterate the code between architect.validate and architect.certify — even a single character — cert rejects with code_fingerprint_mismatch. Fixing the code voids the run. The recovery path is always: edit code → architect.validate → fresh run_id → architect.certify on the fresh run. Do NOT cert from a stale run_id after iteration; ask the user to re-validate first. WHEN TO CALL: only after architect.validate returned tier=production_ready AND the user wants the certified badge AND the code has not been touched since the validate run. NOT for tier=draft/emerging/not_applicable runs (typed rejections fire — see below). NOT idempotent across attempts: each call is one of the 3 attempts in the retry budget. BEHAVIOR: atomic one-shot single LLM call, ~60-180s server-side at high reasoning effort (small payloads finish faster; observed p99 ~250s; server-side budget is 20 min, ~5× observed max). Exceeds typical MCP-client tool-call idle budget (~60s in Claude Code), so the FIRST notifications/progress event fires at t=0 carrying the run_id. The run is atomic by contract — no in_progress lifecycle, no cancellation, no resume. Updates the persisted run's result_json (public review URL + me.validation_history(run_id=...) reflect the cert outcome). ELIGIBILITY GATE (typed rejection enum on failure): caller must own the run, tier=production_ready, less than 24h old, not already certified, within cert retry budget (max 3 attempts), no other cert call in flight for the same run_id, code fingerprint must match the validated code, AND the submitted payload must be cert-payload-complete (see Payload Completeness below — cert rejects pre-LLM with `payload_incomplete` when an imported module's surface isn't visible in the validate payload that produced this run_id). Rejection reasons (typed Literal): auth_required, paid_plan_required, run_not_found, not_run_owner, not_eligible_tier, not_agentic_component (tier=not_applicable runs), already_certified, certification_age_exceeded, retry_budget_exhausted, code_fingerprint_mismatch, code_fingerprint_missing, code_not_on_file (caller omitted `code` argument AND the 24h cert-retry hold for this run has expired or was never written. Recovery: re-run architect.certify from the same MCP session that ran architect.validate, passing the code explicitly — the server never persists code by design), payload_incomplete (submitted/validated payload imports modules whose contents aren't visible — cert refuses pre-LLM to prevent a false-precision downgrade. Recovery: re-validate with verbatim public-surface stubs for every imported module, then re-cert on the fresh run_id. Empirically validated: PR #157 iter8/iter9 cert rejections were exactly this class — code on disk was correct, the submitted payload merely omitted module visibility), cert_consensus_score_below_threshold (consensus_median<75 — consensus runs only), cert_consensus_unstable_blocker (any principle mode_stability<80% — consensus runs only), run_state_corrupt, cert_persistence_failed, cert_in_flight (a prior architect.certify call on this run_id is still running. Poll me.validation_history for the verdict; do not retry until it resolves). PAYLOAD COMPLETENESS (load-bearing for cert eligibility): the cert reviewer reads the EXACT payload that produced the validate run_id. Imported modules whose surface isn't present in the payload cause pre-LLM `payload_incomplete` refusal. Avoidance — when validating with intent to cert, bundle public-surface stubs for every imported module: `from sqlalchemy.exc import SQLAlchemyError` → include a stub class; `from app.db import models` → include a `class models:` namespace stub with the columns/methods you reference; module-level imports of `dataclass`, `Literal`, `json`, `datetime`, `timezone` MUST also be in the payload (cert correctly catches when they're omitted — code would NameError on import). 'Submit Like Production': the payload should be the code as it would actually run, not a compressed sketch. The stubs cover IMPORTED dependencies only; the certified code's own enforcement branches (approval gates, policy checks, recovery paths) must be present in full. A `# ...` placeholder reads as an ABSENT control and is graded against you, not as shorthand for one that exists. PRE-LLM REJECTION AUDIT TRAIL: when cert rejects before the LLM call (payload_incomplete, code_fingerprint_mismatch, etc.), `certification_attempts=[]` on the response — no attempt landed in the retry budget, no LLM hop occurred. The rejection envelope's `rejection_reason` + `guidance` are the actionable surface. (Audit-trail UI surfacing of pre-LLM rejections is tracked in the platform self-audit set as anomaly #5; out of scope for the cert tool itself.) INPUTS: re-send the SAME code that produced the run_id (the architect persists findings + recommendations, never code, by design — privacy-preserving). Server compares the submitted code's SHA-256 fingerprint to the stored fingerprint and rejects mismatches. Auth: Bearer <token>, Pro or Teams plan required. UK/EU data residency (Cloud Run europe-west2). Code processed transiently by OpenAI (no-training-on-API-data) and dropped; payloads JSON-escaped + delimited as inert untrusted data — prompt-injection inside code is ignored. If the cert call fails outright (provider error, persistence error), a fresh architect.certify is the recovery path; the eligibility gate enforces the 3-attempt retry budget. For long-running cert workflows the answer is to re-validate, not to make this tool stateful. OUTCOMES: certification_status ∈ {confirmed_production_ready (badge mints), downgraded_to_emerging (cert review surfaced a missed production_blocker, tier capped at C/emerging), unavailable_provider_error (LLM call failed, retry within budget)}. Cert findings + summary + attempt history surfaced on the persisted run for full inspectability.

  Connector

• get_skill

  civilquants

  Paid tier only. Fetch a senior-QS skill methodology by slug (see list_skills) and APPLY it to the user's documents — the returned body is the system instruction for you to run the methodology on the customer's tokens; CivilQuants does not run inference. Paid callers get the full methodology; anonymous/free callers get a TIER_INSUFFICIENT upsell body; a rejected token gets an INVALID_TOKEN re-authenticate body. The document-heavy skills assume you can chunk/parse the customer's files and render a Word pack locally — that needs a code-execution client (Claude Code / Codex / VS Code) and the pack from get_document_pipeline; on a chat connector you can still read and reason with the methodology. Sign up at https://civilquants.com/pricing. Example: get_skill(skill="tender_risk_assessment").

  Connector

• create_account

  mcp

  Sign up for a brand-new sota.io account from inside Claude — no browser, no copy-paste. Two-step flow: STEP 1: Call with just `email`. We send a 6-digit confirmation code to that email. STEP 2: Call again with `email` + `code`. We verify, create the account on the Free tier (3 projects, EU-hosted, no credit card), generate a sota.io API key, and return it to you. After Step 2 you'll get back a key like `sota_…`. **Save it in a safe place** — you'll need it for any subsequent sota.io tool call in Claude (or you can use it with the sota CLI). It is shown ONCE and never recoverable. sota.io is an EU-native PaaS hosted in Germany — GDPR-compliant by default, no CLOUD Act exposure. Disposable / throwaway email addresses are not accepted; use a real address.

  Connector

• ic_get_my_workshop_key

  Immersive Commons

  Retrieve the 5-hour Z.ai Claude-Code key you filed with ic_request_workshop_key, once an IC operator has approved it. Poll with the request_id that ic_request_workshop_key returned. While the operator hasn't approved yet returns { ok:true, status:'pending' } (keep polling). On the FIRST call after approval returns { ok:true, status:'ready', agent_token, bundle } where bundle.copy_paste is the paste-and-go Claude Code setup block. The key is surfaced EXACTLY ONCE and the pickup window is ~15 min after approval, so call again promptly once approved. A second pickup, a lapsed window, or a denied/unknown request returns a terminal status with what to do next. You can only retrieve your OWN request. Args: { request_id }. Required scope: keys:request.

  Connector

• tascan_add_tasks

  TaScan

  Add one or more tasks to an event (task list). Supports bulk creation. IMPORTANT: Set response_type correctly — use "text" for info collection (names, phones, emails, notes), "photo" for visual verification (inspections, serial numbers, damage checks), "checkbox" only for simple confirmations. NOTE: To dispatch tasks to the Claude Code agent running on Mike's PC, use tascan_dispatch_to_agent instead — it routes directly to the agent's inbox with zero configuration needed.

  Connector

• generate_wallet

  Solentic

  Returns runnable code that creates a Solana keypair. Solentic cannot generate the keypair for you and never sees the private key — generation must happen wherever you run code (the agent process, a code-interpreter tool, a Python/Node sandbox, the user's shell). The response includes the snippet ready to execute. After running it, fund the resulting publicKey and call the `stake` tool with {walletAddress, secretKey, amountSol} to stake in one call.

  Connector

• generate_wallet

  Blueprint Agentic Staking (Solentic)

  Returns runnable code that creates a Solana keypair. Solentic cannot generate the keypair for you and never sees the private key — generation must happen wherever you run code (the agent process, a code-interpreter tool, a Python/Node sandbox, the user's shell). The response includes the snippet ready to execute. After running it, fund the resulting publicKey and call the `stake` tool with {walletAddress, secretKey, amountSol} to stake in one call.

  Connector

• get_stats

  fomox402 — Last-Bidder-Wins on Solana

  Public observability snapshot for the fomox402 broker. WHAT IT DOES: returns aggregated MCP traffic + per-tool call telemetry. Read-only, no auth required, no side effects. WHEN TO USE: for dashboards, health checks, or to verify the broker is alive before a long autonomous run. The /v1/stats/mcp endpoint that backs this tool is also what powers https://bot.staccpad.fun/dashboard. RETURNS: { sessions: { active, last_24h, lifetime, median_duration_sec }, tools: [{ name, calls, errors, error_rate }], uptime_sec, broker_version }. VISIBILITY CAVEAT: only counts streamable-HTTP traffic to https://bot.staccpad.fun/mcp. Local stdio MCP clients (e.g. Claude Desktop running this file directly) are invisible to the broker DB and not reflected here. RELATED: list_agents (per-agent activity), get_me (your own stats).

  Connector

• prepare_consult_domain_expert

  Taste

  Get a humantaste.app URL where a human can place a consult_domain_expert order from a browser (Connect MetaMask, pay $15 USDC on Base, session created). Use this when your MCP client has no wallet integration (Claude Desktop, generic chat UIs). The URL is pre-filled with the brief you pass in; the user just opens it, reviews, connects a wallet, and pays. Returns the payment URL and the price. Free.

  Connector

• get_download_url

  Botverse

  Get a presigned HTTPS URL to download the completed output file. Call after get_job_status returns 'complete'. URL expires in 24 hours. NOTE: fetching this URL is a direct S3 download, which is BLOCKED in sandboxed agent environments (claude.ai, Claude Desktop, Cursor). If you are in a sandbox, use get_output_content instead to receive the bytes inline over the tool channel.

  Connector

• get_setup_instructions

  FundingLandscape

  Return MCP setup instructions for Claude Desktop and other clients. Does not count toward your monthly searches.

  Connector

• get_linkedin_status

  LinkedIn MCP Server (Salesbot)

  Check whether the user's LinkedIn account is connected and active. Returns the connection state and, if not connected/blocked, how to fix it. Call this first when another tool returns code ACCOUNT_NOT_CONNECTED or ACCOUNT_BLOCKED. profile_id is optional — defaults to the active/first profile.

  Connector

• install_snippets

  Omnicall — Agent Tools Gateway

  Return ready-to-paste configuration snippets for installing this MCP server in Claude Code, Cursor, Cline, Continue.dev, Windsurf, and Zed. Free.

  Connector

• signal_connect

  local-mcp

  Connect Signal to Local MCP. Reports whether Signal Desktop is installed and signed in, and tells you exactly what to do next — install Signal, or open it and link your phone. (Signal links inside its own desktop app, so the QR is shown there, not here.) Once you're signed in, signal_list_chats / signal_read_messages work. If Signal is already connected, it just reports that.

  Connector