List your agent

AgentWatch

MCP server● Hosted · onlinev0.5.1

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

Reviews

No review yet. Used AgentWatch? Be the first to help others choose.

What it does

AgentWatch is an MCP server, a connector that lets an AI assistant use it as a tool. It is hosted: an assistant connects to it over the internet, nothing to install.

No capability identified yet from its description.

Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence). None of this is a test of the tool.

At a glance

Hosted (remote)YES
Local installNO
Version0.5.1
PriceNot in the registry
First seen06 Oct 2026
Last checked5d ago

How to connect

As declared in the Official MCP Registry · hosted endpoint tested by Electra Index 20h ago (live check)

Hosted endpoint

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

In Claude Code: claude mcp add --transport http agentwatch-2 https://agentwatch.agentwatch.workers.dev/mcp

MCP settings (Claude Desktop, Cursor and other MCP clients)

{
  "mcpServers": {
    "agentwatch-2": {
      "url": "https://agentwatch.agentwatch.workers.dev/mcp"
    }
  }
}

Reliability

Re-tested about every 3 days · last check 20h ago
100%Observed availability, 30 days · 10 checks
10 / 0Answers / failures, 30 days
No key neededAccess status (latest answer)
Observed test history · one mark = one check
25 Oct20 Nov
AnsweredAnswered, key requiredNo valid answer

Observed endpoint availability: the share of our conclusive checks that got an answer. A request for a key or sign-in counts as an answer (the server is up, its access is protected). Timeouts, unreachable endpoints, server errors and invalid MCP replies count as failures; rate-limited checks and checks during our own incidents are not counted. This is what we observed at each check, not continuous uptime: an outage between two checks may go unseen. The 90-day figure will appear once 90 days of checks exist (checks since 19 Oct 2026). How we measure

Tool changes

Tool tracking since 13 Nov 2026 · test history since 19 Oct 2026

No tool added or removed since tracking started. 21 tools in the latest list.

Changes are confirmed by comparing complete tool lists only, read about every 3 days, and dated by the day we saw them. A renamed tool appears as one removal and one addition.

Live check

Electra Index connected to the hosted endpoint 20h ago

ONLINE AgentWatch answered an MCP connection on 20 Nov 2026 and introduced itself as agentwatch 0.5.1 (MCP protocol 2025-03-26).

21 tools offered to AI assistants

  • 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
  • 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): appe
  • add_watch · Start watching an address. Use when onboarding a new agent or Safe.
Show 9 more
  • 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 activit
  • 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 on
  • 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 A

What "online" means: the server answered an MCP connection at the time of the check. It is not a guarantee of security, quality or continuous uptime. How we test: we open an MCP session and ask for the tool list, as an AI assistant would. We never run a tool and never send a key. Re-tested about every 3 days. Method

Is this your server? Monitoring Pro: a check every 30 minutes and an email within the hour when it stops answering. Launch offer: $39.99 once, for life.

Facts & evidence

Each fact shows where it was seen and when.
FactValueEvidenceSourceLast confirmed
Hosted endpointhttps://agentwatch.agentwatch.workers.dev/mcpDECLAREDSRC-001 Official MCP Registry5d ago
Local install (package)noDECLAREDSRC-001 Official MCP Registry5d ago
Remote access (hosted)yesDECLAREDSRC-001 Official MCP Registry5d ago
Websitehttps://agentwatch.agentwatch.workers.devDECLAREDSRC-001 Official MCP Registry5d ago
Registry statusactiveDECLAREDSRC-001 Official MCP Registry5d ago
Version0.5.1DECLAREDSRC-001 Official MCP Registry5d ago
MCP serveryesDECLAREDSRC-001 Official MCP Registry5d ago

Change history

  • NEW06 Oct 2026
    first seen in the index

Is this page accurate?

Flag it and our robot re-checks the official source. Reports never change a score.

Do you run AgentWatch? Know when it stops answering

For publishers · optional

Its hosted endpoint can be monitored. Monitoring Pro connects every 30 minutes like an AI assistant, emails you within the hour when it stops answering, keeps a 90-day availability history and adds your answer rate to your badge.

Monitor AgentWatchLaunch offer $39.99 once, for life instead of $9.99/month · All plans

Monitoring never changes a score or a rank.

Are you the publisher of AgentWatch?

Free · show your listing

An independent listing builds trust with your buyers. Announce it, and add the badge to your website or README.

Announce it on LinkedIn
Listed on Electra IndexListed on Electra Index
<a href="https://electraindex.com/mcp/agentwatch-2?utm_source=badge&utm_medium=share&utm_campaign=listing"><img src="https://electraindex.com/api/badge/agentwatch-2/card" width="260" height="72" alt="Listed on Electra Index"></a>

Questions about AgentWatch

How do I connect AgentWatch?

Use the hosted endpoint https://agentwatch.agentwatch.workers.dev/mcp in your assistant's MCP settings. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.

What tools does AgentWatch offer?

When Electra Index connected on 20 Nov 2026, it listed 21 tools: list_watched, get_feed, run_audit, get_capabilities, get_alerts, get_pending_proposals, get_fidelity, get_leaderboard and more. The full list is in "Live check" above.

Is AgentWatch online?

Yes. Its hosted endpoint answered an MCP connection from Electra Index 20h ago.