# AgentWatch

- Registry name: `dev.workers.agentwatch.agentwatch/agentwatch` · version 0.5.1
- Categories (automatic, keyword rules): Monitoring & logs, Infrastructure & security, Crypto & blockchain, Finance & markets, Markets & trading
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=dev.workers.agentwatch.agentwatch%2Fagentwatch
- Server page: https://mcpstation.net/s/dev.workers.agentwatch.agentwatch--agentwatch.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://agentwatch.agentwatch.workers.dev/mcp`

## Tools (as reported by the server, not verified)

- `list\_watched`: List 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\_feed`: Decoded activity feed for an address. Use when reviewing what an agent did on-chain.
- `run\_audit`: Run provenance audit on a Safe/address. Use when the user asks 'is this fake?' or wants a shareable verdict.
- `get\_capabilities`: Blast-radius / historical capability for an agent key. Use before trusting an agent with funds.
- `get\_alerts`: List alerts scoped to this principal's watched addresses \(empty watch list → call watch\_demo\_set first\). Use when checking what needs attention.
- `get\_pending\_proposals`: Pending Safe multisig proposals from the Safe Transaction Service \(indexer confidence\). Pass safe=0x… or omit to scan all watched addresses.
- `get\_fidelity`: Intent↔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 is vacuous.
- `get\_leaderboard`: Public 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, and what it would need to climb. Read-only: nothing here can be self-reported.
- `get\_benchmark`: Counterfactual 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\_tca`: TCA market-context snapshot for an event\_id \(chain:txHash\). Use when judging execution quality.
- `register\_intent`: Declare 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 \(empty data + value\>0\): appending reverts on Safe/fallback handlers; register without a
- `add\_watch`: Start watching an address. Use when onboarding a new agent or Safe.
- `watch\_demo\_set`: ONE-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 dashboard has recent activity. Call this FIRST after connect when list\_watched is empty,
- `refresh\_watches`: Force 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 focus the pass.
- `get\_agent\_passport`: Read 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\_passport`: Declare 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; publishing exposes only this address, never the rest of the watch list.
- `list\_recovery\_owners`: List 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\_owner`: Save 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\_owner`: Remove a saved recovery address for this user.
- `get\_safe\_defaults`: Return 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\_dashboard`: Persona-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 to Always allow the AgentWatch MCP App widget when the host prompts.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html