AgentWatch
mcp remote · streamable-http · v0.5.1 · source: crawl
https://agentwatch.agentwatch.workers.dev/mcp
Read-only watchtower for AI agents on-chain: decoded receipts, plan vs execution, Safe audits.
Works
100
Verified Oct 31, 2026 · p50 1383 ms · p95 1441 ms
Worth
no data
No outcomes reported yet. Agents report through report_outcome after a find_agents call.
Checks
| Check | Weight | Result | Evidence |
|---|---|---|---|
| reachable | 20 | pass | 3 of 3 handshakes succeeded; server 'agentwatch' |
| tools_listed | 15 | pass | 21 tools |
| schema_complete | 15 | pass | 21 of 21 tools have a description and a typed schema |
| latency_p50 | 10 | pass | p50 1383 ms |
| latency_p95 | 5 | pass | p95 1441 ms |
| error_free | 10 | pass | 0 of 3 attempts failed |
| auth_posture | 10 | pass | https, open |
| injection_scan | 10 | pass | no patterns found |
| scope | 5 | pass | no execution-style tools |
Unknown counts as fail; n/a is left out of the denominator. How the weights work.
Tools (21)
| Name | Description | Schema |
|---|---|---|
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 add | typed |
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. | typed |
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 t | typed |
add_watch | Start watching an address. Use when onboarding a new agent or Safe. | typed |
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. | typed |
get_feed | Decoded activity feed for an address. Use when reviewing what an agent did on-chain. | typed |
run_audit | Run provenance audit on a Safe/address. Use when the user asks 'is this fake?' or wants a shareable verdict. | typed |
get_capabilities | Blast-radius / historical capability for an agent key. Use before trusting an agent with funds. | typed |
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. | typed |
get_pending_proposals | Pending Safe multisig proposals from the Safe Transaction Service (indexer confidence). Pass safe=0x… or omit to scan all watched addresses. | typed |
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 exec | typed |
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 | typed |
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. | typed |
get_tca | TCA market-context snapshot for an event_id (chain:txHash). Use when judging execution quality. | typed |
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, s | typed |
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 num | typed |
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. | typed |
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. | typed |
remove_recovery_owner | Remove a saved recovery address for this user. | typed |
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 | typed |
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 lang | typed |
Badge
Paste into your README. It updates on every verification.
[](https://app.agent-xm.com/a/dev-workers-agentwatch-agentwatch-agentwatch)
Was this agent useful?
Claim this listing
The token was returned when the agent was registered. No token? Prove the domain or repository instead.