Agent Watch
https://agent-watch-api-production.up.railway.app/mcp/ ↗
Description
Monitoring for the agent economy — liveness, latency, trust scoring for MCP endpoints
What our measurements say
Agent Watch is a remote MCP server published at agent-watch-api-production.up.railway.app. It has been probed 6 times since 9/12/2026. It answered in 6 of them (100.0%), a near-uninterrupted record. Median response time is 386 ms, placing it among the faster endpoints. It offers a narrow, focused set of 6 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Agent readability score
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Agent readability score
Strengths
- Tool names like 'aw_health' and 'aw_check_endpoint' clearly indicate their purposes.
- Descriptions for 'aw_census' and 'aw_alerts' provide actionable context for usage scenarios.
Weaknesses
- Truncated descriptions (e.g., 'aw_census' cuts off mid-sentence) reduce clarity.
- Parameter 'watch_token' in 'aw_watch' lacks clear explanation of its purpose.
- No explicit error handling or constraints documented in tool descriptions.
aw_census— Description truncated mid-sentence, missing critical details about 'unknown' state definitions.aw_watch— Parameter 'watch_token' lacks explanation of its role in plan limits.
Verdict
Event narrative
Sign up free to generateRaw observations
Schema compliance
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
- tools/list schema valid
- inputSchema is valid JSON Schema
- Smoke test not run this round
- Cold-start: cold 183ms → warm 180ms (penalty 3ms)
Tools
Tools the server advertised in the latest measurement — measured, not catalog-claimed.
aw_healthLiveness check for the Agent Watch API. Returns ok, service name, and version. Call this first to verify connectivity before using other tools.
aw_check_endpointProbe an MCP or HTTP-402 endpoint now and get its trust verdict. Performs a real MCP initialize handshake (not a ping), measures p50/p95 latency, counts tools, hashes the tool schema (for drift detection), and checks RFC 9728 auth metadata. Returns: alive (bool), name, tool_count, latency_p50_ms, tool_schema_hash, auth_metadata_present, and error detail when dead. Use before wiring any new MCP server into your client. Args: url: the MCP or HTTP-402 endpoint URL to probe (e.g. https://host/mcp/) timeout: probe timeout in seconds (default 30)
urlstringrequiredtimeoutinteger
aw_censusFull-census summary of the official MCP registry: 7,454 endpoints probed with real MCP handshakes. Returns alive/dead/unknown counts and percentages. States: alive = MCP initialize succeeded; dead = no answer; unknown = answered but auth-gated (401/403/402) or redirecting — liveness unprovable without credentials. Use to quantify how much of the MCP ecosystem is actually reachable.
aw_list_monitoredList all endpoints in the Agent Watch census with their registry names. Returns count and the full endpoint list (URLs). Combine with aw_alerts to find which of these are dead. Read-only.
aw_alertsShow dead endpoints across the monitored registry (alive=false). Returns up to 500 dead endpoints with names. Use after aw_census or aw_list_monitored to get the actionable dead list. Read-only.
aw_watchAdd endpoints to your personal watchlist (probed immediately, then every 6h). Plan-limited by the email used at checkout: free 5, Builder ($19/mo) 50, Team ($99/mo) 500 endpoints. Alerts fire on alive→dead transitions and tool-schema drift. Already-watched URLs are returned without re-probing. Args: email: the email your subscription is under (free tier works too) urls: endpoint URLs to add to your watchlist watch_token: issued at registration, delivered in your onboarding email — required
emailstringrequiredurlsarrayrequiredwatch_tokenstring
Availability history
Event log
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
- Added to watch — era: Legacy
Get your badge
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/io-github-entradox-agent-watch)<a href="https://mcpmetrics.io/servers/io-github-entradox-agent-watch"><img src="https://mcpmetrics.io/badge/io.github.entradox/agent-watch/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to seeSimilar MCP servers
The catalog entries whose name and description are closest to this one, found with the same index the search box uses.
- Agentry — The Trust Layer for the Agent Economyapi.agentry.com
Agent registry with Nostr identity, reputation, escrow, observability, and Lightning payments.
- Is It Trust Ready — agent-trust-readiness scannerapi.isittrustready.ai
Scan any website or MCP server for agent-trust-readiness; returns a signed, verifiable scorecard.
- AIﾉアカリ☆ Agent Trust Receiptai-akari.ai
Read-only Remote MCP for externally grounded AI agent trust receipts.
- io.github.jdhart81/agent-trust-oraclemcp.viridisconservation.com
Decay-weighted reputation + tamper-evident trust attestations for the agent economy.
- Free Agent Economy Labaustere-unsteady-pdf.replit.app
Free buyer-side outcome verification and provider comparison for supplied agent receipts.
- HiveGate — Hive Civilization Agent Trust & Settlementhivegate.hiveagentiq.com
Trust & settlement for AI agents: DID, ZK reputation, audit, USDC/USDCx/USAD/ALEO. First DID free.
Comments
Sign in to write a comment
No comments yet. Be the first.