Agent Watch

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Monitoring for the agent economy — liveness, latency, trust scoring for MCP endpoints

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Agent Watch": {
      "url": "https://agent-watch-api-production.up.railway.app/mcp/",
      "transport": "streamable-http"
    }
  }
}

Measured tools (8)

• aw_health read-only

  Liveness check for the Agent Watch API. Returns ok, service name, and version. Call this first to verify connectivity before using other tools.

  Hints: read-only yes · destructive no · idempotent yes · open-world not declared

• aw_check_endpoint read-only

  Probe 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)

  Parameters:

  • url (required) — string
  • timeout — integer

  Hints: read-only yes · destructive no · idempotent yes · open-world not declared

• aw_census read-only

  Full-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.

  Hints: read-only yes · destructive no · idempotent yes · open-world not declared

• aw_list_monitored read-only

  List 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.

  Hints: read-only yes · destructive no · idempotent yes · open-world not declared

• aw_alerts read-only

  Show 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.

  Hints: read-only yes · destructive no · idempotent yes · open-world not declared

• aw_watch

  Add 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

  Parameters:

  • email (required) — string
  • urls (required) — array
  • watch_token — string

  Hints: read-only no · destructive no · idempotent yes · open-world not declared

• skills_list_tool

  List this product's skills. Each entry carries the SKILL.md URI, its name and description, verbatim frontmatter, and a per-file sha256 manifest. Read a body with `read_skill`.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• read_skill

  Read a product skill file by its skill:// URI. Args: uri: e.g. skill://<product>/<skill-name>/SKILL.md Get valid URIs from `skills_list_tool`.

  Parameters:

  • uri (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.