AgentWatch
Server Details
Read-only watchtower for AI agents on-chain: decoded receipts, plan vs execution, Safe audits.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-03-26
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 21 tools
Many tools are distinct resources (register_intent, run_audit, get_safe_defaults), but there is a cluster of agent-scoring reads—get_fidelity, get_benchmark, get_capabilities, get_agent_passport, get_leaderboard—that overlap in purpose and could be misselected, plus get_dashboard acting as an aggregate of several others. Descriptions mitigate this somewhat, but the boundaries between trust/score-oriented tools require careful reading.
Names are uniformly snake_case and follow recognizable verb_noun patterns (get_feed, list_watched, add_watch, set_recovery_owner, register_intent). The mix of get_ vs list_ read prefixes is minor, and watch_demo_set is a slight outlier, but overall the convention is predictable.
At 21 tools the surface is heavy and sits in the borderline 16-25 range; several separate get_* metric tools could plausibly be consolidated. Each tool does have a role, but the volume makes the set harder to navigate than its purpose strictly requires.
Coverage spans watch lifecycle, identity/passport, alerts, fidelity/benchmark/capability scoring, Safe proposals, recovery owners, intent registration, and audits—broad for the domain. The notable gap is the absence of a remove_watch / unfollow operation, and recovery owners have full CRUD while watches do not.
Available Tools
21 toolsadd_watchBInspect
Start watching an address. Use when onboarding a new agent or Safe.
Inputs: address (required), label, chains.
get_agent_passportAInspect
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.
Inputs: address (required).
get_alertsBInspect
List alerts scoped to this principal's watched addresses (empty watch list → call watch_demo_set first). Use when checking what needs attention.
Inputs: status.
get_benchmarkBInspect
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.
Inputs: agent_key (required).
get_capabilitiesBInspect
Blast-radius / historical capability for an agent key. Use before trusting an agent with funds.
Inputs: agent_key (required).
get_dashboardAInspect
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.
Inputs: persona.
get_feedBInspect
Decoded activity feed for an address. Use when reviewing what an agent did on-chain.
Inputs: address (required), since.
get_fidelityBInspect
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.
Inputs: agent_key (required).
get_leaderboardAInspect
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.
Inputs: limit, agent_key.
get_pending_proposalsBInspect
Pending Safe multisig proposals from the Safe Transaction Service (indexer confidence). Pass safe=0x… or omit to scan all watched addresses.
Inputs: safe, chains.
get_safe_defaultsAInspect
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.
Inputs: agent_key (required), chain, purpose, all_recoveries, +1 more.
get_tcaBInspect
TCA market-context snapshot for an event_id (chain:txHash). Use when judging execution quality.
Inputs: event_id (required).
list_recovery_ownersAInspect
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.
Inputs: no named parameters.
list_watchedAInspect
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.
Inputs: no named parameters.
refresh_watchesAInspect
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.
Inputs: chains, address.
register_intentAInspect
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.
Inputs: agent_key (required), description (required), expected, declared_at, +1 more.
remove_recovery_ownerCInspect
Remove a saved recovery address for this user.
Inputs: address (required).
run_auditBInspect
Run provenance audit on a Safe/address. Use when the user asks 'is this fake?' or wants a shareable verdict.
Inputs: address (required), chain, agents.
set_agent_passportAInspect
Declare who a watched agent is: model provider, run cadence, role, purpose, operator, and whether to publish a shareable public passport at /a/. Declarations never change the receipt-derived numbers next to them; publishing exposes only this address, never the rest of the watch list.
Inputs: address (required), role, model, public, +5 more.
set_recovery_ownerAInspect
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.
Inputs: address (required), label, purpose, make_default.
watch_demo_setAInspect
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.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Audit AI agents' tool calls, planning and memory; Base on-chain data; pay per call via x402.
Proof-of-spend and reserve checks for AI agents: receipts, spend audit, NAV, reconciliation.
Read-only smart-contract security intelligence for autonomous agents.
Signed, append-only receipts of an AI agent's decisions and outcomes, with public proof links.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides cryptographic governance receipts for AI agents, enabling pre-execution evaluation and signed verdicts (EXECUTE/BLOCK/REVIEW/SHADOW) with offline-verifiable audit trails.MIT
- AlicenseAqualityBmaintenanceCryptographic accountability for AI agents. Ed25519-signed receipts for every MCP tool call. Constraints, chains, AI judgment, invoicing, and local dashboard included.244 npm1MIT
- AlicenseNot gradedqualityDmaintenanceSecurity layer for AI agents that evaluates transaction intents and returns verdicts (ALLOW/WARN/DENY) using deterministic rules, on-chain checks, and simulation.15 npmMIT

evermint-mcpofficial
AlicenseNot gradedqualityDmaintenanceTamper-evident receipts for AI agent actions. The notary layer for agent-to-agent transactions.40 npm1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.