MCP server

AgentWatch

dev.workers.agentwatch.agentwatch/agentwatch

Checked 25 Oct 2026, 20:29 UTC · Connected to it and listed its tools

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

Website

At a glance

Type

MCP server

Publisher

Not verified

Status

Working at last check

Tools

21

Token cost

About 2,882 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

25 Oct 2026, 20:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http agentwatch https://agentwatch.agentwatch.workers.dev/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.agentwatch]
url = "https://agentwatch.agentwatch.workers.dev/mcp"

Gemini CLI

{"mcpServers":{"agentwatch":{"httpUrl":"https://agentwatch.agentwatch.workers.dev/mcp"}}}

Cursor

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

VS Code

{"servers":{"agentwatch":{"type":"http","url":"https://agentwatch.agentwatch.workers.dev/mcp"}}}

Antigravity

agy mcp add agentwatch https://agentwatch.agentwatch.workers.dev/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"agentwatch","server_url":"https://agentwatch.agentwatch.workers.dev/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"agentwatch","server_url":"https://agentwatch.agentwatch.workers.dev/mcp"}

Tools

• add_watch ~102 tokens
  Start watching an address. Use when onboarding a new agent or Safe.
• get_agent_passport ~103 tokens
  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.
• get_alerts ~74 tokens
  List alerts scoped to this principal's watched addresses (empty watch list → call watch_demo_set first). Use when checking what needs attention.
• get_benchmark ~100 tokens
  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_capabilities ~70 tokens
  Blast-radius / historical capability for an agent key. Use before trusting an agent with funds.
• get_dashboard ~134 tokens
  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.
• get_feed ~95 tokens
  Decoded activity feed for an address. Use when reviewing what an agent did on-chain.
• get_fidelity ~120 tokens
  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 ~164 tokens
  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_pending_proposals ~115 tokens
  Pending Safe multisig proposals from the Safe Transaction Service (indexer confidence). Pass safe=0x… or omit to scan all watched addresses.
• get_safe_defaults ~233 tokens
  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_tca ~66 tokens
  TCA market-context snapshot for an event_id (chain:txHash). Use when judging execution quality.
• list_recovery_owners ~82 tokens
  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.
• list_watched ~77 tokens
  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.
• refresh_watches ~151 tokens
  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_intent ~298 tokens
  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
• remove_recovery_owner ~56 tokens
  Remove a saved recovery address for this user.
• run_audit ~120 tokens
  Run provenance audit on a Safe/address. Use when the user asks 'is this fake?' or wants a shareable verdict.
• set_agent_passport ~386 tokens
  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.
• set_recovery_owner ~189 tokens
  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.
• watch_demo_set ~147 tokens
  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,

Browse

• Crypto and blockchains

Related MCP servers

• Tanod Chain
  EVM and Solana reads: balances, tokens, eth_call, logs, receipts, gas, blocks, transactions, ENS.
• Altscan explorers
  Keyless, read-only BNB Chain and Ethereum data: transactions by hash, tokens with a lookalike check
• SwapChan
  Find money in any wallet, best-price swaps, simulate, PnL, pools, whales, contract and bridge tools.
• Parallax Protocol
  Read-only Parallax PoW chain data: blocks, transactions, mining, supply, explorer and network health
• LION — Verified Company & Compliance Data
  Keyless x402 compliance on Base: $0.001 OFAC wallet screen, $0.05 pack, $0.95 company file.
• Ankr Agent RPC
  Read chain data on 200+ networks and Sui: transactions, logs, balances, objects, ABI-decoded.
• US Company Intelligence for AI Agents (SEC EDGAR, x402)
  SEC EDGAR company briefs for agents: cited synthesis, XBRL metrics. x402/USDC, no account.
• Watchtower
  Job alerts for AI agents: describe a role once, get only new postings from 1,500+ tech job boards.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/dev.workers.agentwatch.agentwatch/agentwatch.svg)](https://aptlynx.net/servers/dev.workers.agentwatch.agentwatch/agentwatch)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents