Agents Index

AgentWatch

Online

Read-only watchtower for AI agents on-chain: decoded receipts, plan vs execution, Safe audits.

Visit publisherConnectJSON

What it can do: 21 tools

  • list_watchedList watched addresses for this connector principal. NEW USERS: if empty, call watch_demo_set next (do not invent a global feed), then get_dashboard.
  • get_feedDecoded activity feed for an address. Use when reviewing what an agent did on-chain.
  • run_auditRun provenance audit on a Safe/address. Use when the user asks 'is this fake?' or wants a shareable verdict.
  • get_capabilitiesBlast-radius / historical capability for an agent key. Use before trusting an agent with funds.
  • get_alertsList alerts scoped to this principal's watched addresses (empty watch list → call watch_demo_set first). Use when checking what needs attention.
  • get_pending_proposalsPending Safe multisig proposals from the Safe Transaction Service (indexer confidence). Pass safe=0x… or omit to scan all watched addresses.
  • get_fidelityIntent↔execution fidelity score for an agent or Safe. Use for accountability / coverage meter. Check matched_agent — false means the address has no indexed activity (as signer or as the Safe that executed), so the score
  • get_leaderboardPublic standings for agents with a published passport, ranked from receipts (declared-first coverage, fidelity, reliability, hygiene, sustained work). Pass agent_key to get that agent's own rank, its component scores, an
  • get_benchmarkCounterfactual P&L / agent alpha vs do-nothing baselines. Use for performance honesty checks. Check matched_agent — false means the key has no indexed activity.
  • get_tcaTCA market-context snapshot for an event_id (chain:txHash). Use when judging execution quality.
  • register_intentDeclare an intent BEFORE broadcasting. Returns {intent_id, pairing_code}. Append the 16-hex pairing_code as the last 8 bytes of calldata (no magic prefix), then broadcast — EXCEPT bare ETH transfers to contracts (empty d
  • add_watchStart watching an address. Use when onboarding a new agent or Safe.
  • watch_demo_setONE-SHOT cold-start for brand-new Claude / MCP users with an empty watch list. Adds the July 18 fixture (Agent EOA + Safe A + Safe B on Base, with declared intents) and one live Polygon trading bot, so the first dashboar
  • refresh_watchesForce an immediate poller pass over this principal's watched addresses (catch up txs from explorers into AgentWatch). Use after add_watch / a fresh broadcast when get_feed is still empty. Optional address / chains to foc
  • get_agent_passportRead the declared identity of a watched agent (name, model provider, how often it runs, role, purpose, operator) and whether its public passport page is published.
  • set_agent_passportDeclare who a watched agent is: model provider, run cadence, role, purpose, operator, and whether to publish a shareable public passport at /a/<slug>. Declarations never change the receipt-derived numbers next to them; p
  • list_recovery_ownersList this user's saved recovery wallets (human co-signers for default 1/2 Safes). Each may have a label/purpose — users often keep several for different vaults.
  • set_recovery_ownerSave or update a recovery address for this user. Product default Safe is then 1/2: threshold 1, owners = [agent, this recovery]. Use make_default=true to prefer this label in get_safe_defaults.
  • remove_recovery_ownerRemove a saved recovery address for this user.
  • get_safe_defaultsReturn the default Safe ownership plan for an agent EOA: threshold 1 + agent + selected recovery (1/2 when one recovery is set). Call before register_intent for Safe deploys. AgentWatch never deploys or signs.
  • get_dashboardPersona-tailored dashboard brief (fidelity, alerts, pending plans, recent planned-vs-executed). NEW USERS with empty watches: call watch_demo_set first, then get_dashboard again. Narrate in plain language; ask the user t

Connect it

Claude Code
claude mcp add --transport http agentwatch https://agentwatch.agentwatch.workers.dev/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://agentwatch.agentwatch.workers.dev/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "agentwatch": {
      "url": "https://agentwatch.agentwatch.workers.dev/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "agentwatch": {
      "type": "http",
      "url": "https://agentwatch.agentwatch.workers.dev/mcp"
    }
  }
}

Questions

What does AgentWatch do?

Read-only watchtower for AI agents on-chain: decoded receipts, plan vs execution, Safe audits. It exposes 21 tools to AI assistants.

What tools does AgentWatch provide?

21 tools, including list_watched, get_feed, run_audit, get_capabilities, get_alerts, get_pending_proposals, get_fidelity, get_leaderboard, get_benchmark, get_tca, register_intent, add_watch….

How do I connect AgentWatch to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://agentwatch.agentwatch.workers.dev/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does AgentWatch require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is AgentWatch online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes AgentWatch?

agentwatch.agentwatch.workers.dev. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Agents & Orchestration