AgentWatch is answering right now. Last checked 10 min ago. It exposes 21 tools.
Read-only watchtower for AI agents on-chain: decoded receipts, plan vs execution, Safe audits.
Uptime history
28 days of history · worst day 98%
28 days agonow
100.0%
Uptime 24h
91 of 91 checks
21
Tools
read from the server
568 ms
Response time
average over 24h
open, no key
Access
streamable-http
What the code does
We have not read this server's code yet · tools taken from the live server
Evidence
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
Claims read-only, but ships mutating tools
remove_recovery_owner
заявлено «только чтение», но есть remove_recovery_owner
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found things in this code
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch AgentWatch and you get told the day something new turns up.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.
run in your terminal
claude mcp add agentwatch --transport http https://agentwatch.agentwatch.workers.dev/mcpSettings → Connectors → Add custom connector, then paste this address
https://agentwatch.agentwatch.workers.dev/mcp~/.codex/config.toml
[mcp_servers.agentwatch]
url = "https://agentwatch.agentwatch.workers.dev/mcp".cursor/mcp.json
{
"mcpServers": {
"agentwatch": {
"url": "https://agentwatch.agentwatch.workers.dev/mcp"
}
}
}.vscode/mcp.json
{
"servers": {
"agentwatch": {
"type": "http",
"url": "https://agentwatch.agentwatch.workers.dev/mcp"
}
}
}Available tools 21
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
recovery
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.
remove_recovery_owner
Remove a saved recovery address for this user.
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.
agent
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.
watch
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, then call get_dashboard (Always allow the App). Idempotent — skips addresses already watched.
alerts
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.
audit
run_audit
Run provenance audit on a Safe/address. Use when the user asks 'is this fake?' or wants a shareable verdict.
benchmark
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.
capabilities
get_capabilities
Blast-radius / historical capability for an agent key. Use before trusting an agent with funds.
dashboard
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.
feed
get_feed
Decoded activity feed for an address. Use when reviewing what an agent did on-chain.
fidelity
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.
leaderboard
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.
pending
get_pending_proposals
Pending Safe multisig proposals from the Safe Transaction Service (indexer confidence). Pass safe=0x… or omit to scan all watched addresses.
refresh
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.
register
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 suffix and use expected.steps for multi-leg flows (e.g. approve+supply). Pairing codes are single-use and only consumed by successful (non-reverted) txs. Use deadline_minutes (relative) — normalized to absolute constraints.deadline at registration.
safe
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.
tca
get_tca
TCA market-context snapshot for an event_id (chain:txHash). Use when judging execution quality.
watched
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.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://agentwatch.agentwatch.workers.dev/mcp | streamable-http | answering | 180 ms | 10 min ago |
Alternatives to AgentWatch
same job, measured the same wayMCP SEO Auditor
by petrovicistefan
Read-only static SEO audits and bounded crawling for AI agents.
MCP Android
by dockndevai
Control Android devices over ADB from AI agents — safe-by-default, read-only by default, audited.
Agent Replay
by mdfifty50-boop
Record and replay AI agent execution for debugging
Proof Layer
by world-999-labs
Signed, hash-chained provenance receipts for AI agent actions.
A2db
by agentic-eng
Safe, read-only database access for AI agents. 5 databases, batch queries, SQLGlot.
gws-admin-mcp
by antct11
Safe Google Workspace admin for AI agents: read-only by default, confirm-gated deletes, audit log.
Codebase Doctor
by subhajitlucky
Read-only codebase audits for coding agents: secrets, RLS, deps, review verdicts. No writes.
Recon Kit MCP
by nan786521
Read-only network & security recon tools (DNS, TLS, headers, CORS) for AI agents, each graded.
AgentWatch — questions
Answers built from our own checks of this server.
What can AgentWatch do?
It exposes 21 tools, read directly from the server on our last check. Among them: add_watch, get_agent_passport, get_alerts, get_benchmark, get_capabilities, get_dashboard and 15 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
What is AgentWatch mostly used for?
Its tools cluster around recovery, watch and agent. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is AgentWatch working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 568 ms. The bar chart above shows every period we have measured.
How do I connect AgentWatch?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does AgentWatch need an API key?
No. AgentWatch completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 21 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is AgentWatch?
It answers our handshake in 568 ms on average, which is faster than 20% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.