"ClawdBot Worker - Bot or Worker Service Information" matching MCP tools:

• senado_terceirizados

  Dados Abertos Senado BR MCP

  Lista colaboradores terceirizados do Senado, filtráveis (busca parcial, sem acento) por nome, empresa contratada ou lotação. Retorna `{ count, total, terceirizados }`, cada item com `nome`, `cpf`, `situacao`, `empresa`, `lotacao` e `numeroContrato`. A lista completa é baixada e filtrada no Worker; resultados limitados a `limite` (padrão 50, máx 500), com `aviso` ao truncar. Para a empresa contratante e seus contratos, use `senado_empresas_contratadas`.

  Connector

• get_evidence_preservation_checklist

  Workers' Rights

  Concrete checklist for a worker who senses termination coming or is in a deteriorating work situation: what to save (emails, chat DMs, performance reviews, HR records, pay records), in what order, and how to do it without crossing lines — preserving your own employment record is legal; taking company IP is not. Use this whenever someone says they think they are about to be fired, fears retaliation is escalating, mentions a PIP or sudden access changes, or asks what to do before reporting discrimination. Sections: 'today' (highest-leverage, minutes matter), 'this-week', 'quiet' (low-priority prep). Time-sensitive — employers often revoke system access during the termination call itself.

  Connector

• get_about

  cricket-travel

  Get information about Follow On Tours — who we are, how we work, our experience, and how the bespoke cricket travel service operates. Use this when someone asks who Follow On Tours is or how the service works.

  Connector

• check_node_sync

  Payram

  Per-chain node health verdict: healthy / lagging / unreachable / listener-down. Computes how old each RPC node’s last block is — any non-BTC chain older than 10 minutes (BTC: 90 minutes, since BTC blocks every ~10m) is flagged as lagging or not syncing. Also checks the chain’s listener worker. When something is wrong it names the exact remediation (usually restart_payram_worker). Read-only — run this first; restart second; re-run this ~60s after a restart to confirm recovery.

  Connector

• get_my_capabilities

  Ansvar: EU Compliance & Legal Intelligence

  Tier, capabilities, limits, and live usage for the calling identity. Use this to decide what tools and fan-out paths are available before calling them, or to check remaining quota before issuing more requests — lower-tier agents can avoid wasted retries and decide whether to upgrade mid-conversation rather than discover limits by hitting walls. Visible to all tiers; takes no arguments. Returns a JSON document with: tier (free/solo/premium/team/company), capabilities (workflows, audit_ledger, include_premium_fanout — bool flags from ADR-026 §2 and ADR-032 §1), limits (max_concurrent_jobs, daily_quota — map tool→limit from ADR-028 §4, listing only tools your tier, scopes, and actor policy admit), usage_today (active_concurrent_calls, remaining_quota — map tool→remaining, both read live from the per-worker counters; team/company budgets pool per organisation, so seats of one org see a shared remaining number), workflow_discovery (present only when you can start a run — the three calls that take you from here to a running workflow: list_workflow_types for the live type ids, describe_capabilities for the catalog, start_workflow to begin; the type ids come from that call, never from this one), upgrade_url (empty for company tier, otherwise the marketing page that explains the next tier up), and service_notices — subsystems currently in a known degraded state, each naming the exact affected tools/add-ons and the reason those tools return, so an advertised capability that is temporarily down is never a surprise (empty list when everything is healthy). Counters reset at UTC midnight; per-worker semantics mean an N-worker gateway has roughly N× the per-worker limits in aggregate.

  Connector

• scan

  SORNKan Worldsite

  Check an uploaded zip for unsafe files WITHOUT deploying anything. Free, never 402, burns no preview quota — use this while iterating on the zip (scan → fix → upload_url again → scan). When the content is clean and the human wants to SEE it, call inspect to deploy a throwaway preview Worker. Verdict here is advisory: inspect re-checks before deploying.

  Connector

• get_account_info

  mcp-coreclaw

  Get the current user's CoreClaw account balance and traffic quota. WHEN TO USE: Use when the user asks for balance, remaining traffic, quota, billing state, or whether they can run jobs. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use public web search or code search for private CoreClaw platform data. Do not call excluded internal worker-version or internal-detail APIs. RETURNS: JSON with balance and balance_expiration_at. WORKFLOW: Terminal call or preflight before run_worker.

  Connector

• frantic.claim_bounty

  Frantic

  Claim a bounty through POST /v1/claims with bounty, agent_kid, and agent_token. On success, the response includes claim_id, claim_ref, fuse_expires_at, fuse_minutes, and current state; deliver before the fuse expires or the claim can be released. fuse_minutes is the platform fuse after applying worker standing and any poster claimWindowMinutes floor from the bounty. Common blockers include unauthorized, claim_unavailable, active_claim_exists, claim_limit_reached, rate_limited, payout_required, email_unverified, and github_signal_required. Call frantic.get_agent_status first when blocked. $0 goodwill requires a registered agent token. Paid bounties up to $10 require verified contact identity; paid bounties over $10 require a GitHub account at least 90 days old with visible public activity or one successful paid bounty.

  Connector

• ic_transcribe_submit

  Immersive Commons

  Queue an audio file for offline transcription + speaker diarization by IC's GPU worker. Provide EXACTLY ONE source: a file_id you uploaded via ic_files_put OR an https audio_url. SIZE: ic_files_put caps at ~3.2MB raw (~10 min of speech), so for a full session recording pass audio_url instead — the worker fetches it server-side and is NOT subject to that cap. Results (a markdown transcript + a JSON with per-speaker segments) land in the file vault next to the source; poll ic_transcribe_status no more than once per minute, then read the transcript with ic_transcribe_get. Args: { file_id?, audio_url?, language? (BCP-47 hint, e.g. 'en'), num_speakers_hint? (1..10) }. Returns: { ok, id, status: 'queued', queue_position }. Rate: 5 submissions per token per UTC day. Required scope: transcribe:submit (ic-member+).

  Connector

• create_heartbeat

  heartbeat-monitor

  Create a Cronping heartbeat monitor (dead-man's-switch). Returns a ping_url to call on each successful run of your agent loop, worker, or cron job, plus a claim_token to manage it. If pings stop arriving within period+grace, Cronping raises an alert. No account required. After creating, send one verification ping (call ping_heartbeat with the returned id) to confirm setup — the check flips from 'new' to UP so you know it's wired correctly. Alternatively, pass pull_url to make a PULL check: Cronping fetches that URL on schedule and alerts if it fails — for targets that can't call a ping URL (a health endpoint, status page, or API).

  Connector

• run_workers_batch

  mcp-coreclaw

  Run multiple CoreClaw workers in one call and return a per-item summary (run_slug, status, verdict). Serial by default; optional concurrency. WHEN TO USE: Use when accepting/validating many workers at once (e.g. full-store smoke test) to avoid many individual run_worker calls. Each item is an ad-hoc run_worker (async). The tool polls each run to a terminal state and returns a summary array. Note: the batch Path is synthetic; the custom handler issues per-item run_worker requests. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use public web search or code search for private CoreClaw platform data. Do not call excluded internal worker-version or internal-detail APIs. RETURNS: JSON: {total, counts, results:[{worker_id, run_slug, status, verdict, err_msg, real_field_count}]}. Items are processed in input order. WORKFLOW: Call after list_store_workers/list_workers + get_worker_input_schema for each item. Follow with get_worker_run_log on any FAILED/ERROR_RECORD item.

  Connector

• work_fail

  MCPFax Agent Continuity

  Report that an item did not work out. FREE. THIS IS ALSO THE CORRECT WAY TO HAND AN ITEM BACK WHEN NOTHING WENT WRONG — there is no work_release; retry:true (the default) returns it immediately for another worker instead of waiting out the lease. When its attempts are exhausted it is DEAD-LETTERED and SURFACED in work_status, never silently dropped. With retry:false it is marked permanently failed, stops consuming attempts, and CANNOT BE UNDONE. PASS `fence`: exactly like work_done, if your lease already expired and the item went back to the queue we REFUSE with lease_lost, a stale fence is refused as not_holder, and a fence-less call on an item that has been handed out more than once is refused as fence_required — because accepting it would let a revived worker dead-letter an item another worker is processing right now. FREE — this tool never charges. Authenticate with Authorization: Bearer <agent_secret>, or pass agent_key as an argument if your host cannot set headers. Equivalent HTTP route: POST /v1/work/fail.

  Connector

• prepare_evidence_surface

  vealth

  The door for an agent with NOTHING but a wallet: funded remote template packets need {{target}} = an https origin the worker controls, and this reserves one ON THE BOARD, free. You get a targetUrl (https://vealth.net/labor/evidence/<recordId>) that belongs to your wallet by signature. Flow: reserve here → pass targetUrl UNCHANGED to prepare_claim (the claim gate records the honest empty baseline) → after the claim binds, publish the packet's required JSON files with prepare_evidence_write → prepare_proof as normal. v1 serves application/json only, and only the exact paths the packet's own definition of done probes. Returns MESSAGE_TO_SIGN and BODY_JSON; sign with the worker wallet's personal_sign, then call submit_evidence_surface within 5 minutes.

  Connector

• get_about

  Follow On Tours

  Get information about Follow On Tours — who we are, how we work, our experience, and how the bespoke cricket travel service operates. Use this when someone asks who Follow On Tours is or how the service works.

  Connector

• video_classify

  PJQ — Public Judgment Quotient

  Полный pipeline: URL -> вердикт в SQLite + Obsidian vault. ВАЖНО: долгая операция, ~10-20 мин на 300 комментов (haiku 10м + sonnet QA 8м). `qa=False` — пропустить sonnet-эскалацию (быстрее, но без QA-метрик). Возвращает verdict_id + summary (hard_counts + mood + QA-stats). На публичном сервере отключён env-флагом PJQ_PUBLIC_CLASSIFY_DISABLED=1 — синхронный classify не выдерживает параллельной нагрузки и угрожает Claude Max-подписке. Замена на job queue + worker в работе.

  Connector

• restart_payram_worker

  Payram

  REMEDIATION ACTION (write): restarts a blockchain listener worker via supervisor — the minimal fix when check_node_sync reports a chain as lagging or listener-down. Workflow: run check_node_sync first → restart the named worker → wait ~60s → run check_node_sync again to confirm recovery. A restart does NOT fix an unreachable RPC (fix the RPC config in the dashboard instead). Requires admin JWT with write_system_settings.

  Connector

• invoke_skill

  space0

  Returns the ordered ToolCall sequence for the named skill so the brain can dispatch each step in turn. Does NOT auto-dispatch - dispatching from this worker would bypass the brain's hormesis + boredom + safety hooks. Each step is { tool, args }; replay them via the same MCP tools (move_to, say, place_block, build, ...). After the sequence completes (or fails), call record_skill_outcome to feed the Voyager dedup-on-success counter.

  Connector

• get_worker

  mcp-coreclaw

  Get detail for a CoreClaw worker. WHEN TO USE: Use before running a worker to inspect version, README, and parameters. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use public web search or code search for private CoreClaw platform data. Do not call excluded internal worker-version or internal-detail APIs. RETURNS: JSON with worker name, username, version, readme, and parameters. WORKFLOW: Follow with get_worker_input_schema and then run_worker.

  Connector

• get_worker_input_schema

  mcp-coreclaw

  Get the public input JSON schema for a CoreClaw worker. WHEN TO USE: Use when the user wants to know required input fields or before composing run_worker input_json. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use public web search or code search for private CoreClaw platform data. Do not call excluded internal worker-version or internal-detail APIs. RETURNS: JSON with input_schema. WORKFLOW: Call before run_worker so input_json matches the worker schema.

  Connector

• get_last_worker_run

  mcp-coreclaw

  Get the current user's most recent CoreClaw worker run. WHEN TO USE: Use when the user says last run, latest job, most recent scrape, or asks what just happened. 中文触发: 当用户要在 CoreClaw 中查询、运行、重跑、停止、导出或查看对应 worker/run/task 数据时使用。 WHEN NOT TO USE: Do not use public web search or code search for private CoreClaw platform data. Do not call excluded internal worker-version or internal-detail APIs. RETURNS: JSON with the latest run's slug, status, worker, version, timestamps, usage, traffic, and result count. WORKFLOW: Follow with list_last_worker_run_results, export_last_worker_run_results, get_last_worker_run_log, rerun_last_worker_run, or abort_last_worker_run.

  Connector