Agent Watch

io.github.entradoxPublished by GitHub account entradoxv0.1.0Updated Oct 24, 2026

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

VerifiedStreamable HTTPWeb executableDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

Agent Watch is a remote MCP server that lets an assistant probe MCP and HTTP-402 endpoints for liveness, latency and trust, and monitor a personal watchlist.

What you can do
Check service health and version of the Agent Watch API itself before other calls. Probe a single MCP or HTTP-402 endpoint for a trust verdict, including a real MCP initialize handshake, p50/p95 latency, tool count, tool-schema hash and auth metadata. Read a full-census summary of the official MCP registry with alive, dead and unknown counts. List all monitored endpoints and retrieve the dead-endpoint alert list. Add endpoints to a personal watchlist that is probed immediately and then every six hours, with alerts on liveness transitions and schema drift. List and read the product's skill files by URI.
When to use it
Useful when you need to check whether an MCP server or HTTP-402 endpoint is reachable and healthy, compare latency or detect tool-schema drift, or keep a watchlist of endpoints you depend on.
Requirements
A remote streamable HTTP endpoint; no local package, environment variables or headers are declared. Watchlist capacity is tied to the email used at checkout, with free, Builder and Team tiers. Network access to the Agent Watch API and to the endpoints being probed.
Before you install
Adding endpoints to the watchlist is a write action and is plan-limited; paid tiers are involved. Probes send requests to third-party endpoints you name, and results are reported back through the service. No authentication is declared, so treat watchlist ownership as tied to the checkout email.

Installation

In SourceWeft

  1. Open Agent Watch in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.entradox%2Fagent-watch/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

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

README

This repository has no README.

Tools

8

aw_health

Agent Watch Health

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

Takes no parameters.

aw_check_endpoint

Probe MCP Endpoint

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)

Parametersurlrequiredtimeout

aw_census

Registry Liveness Census

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.

Takes no parameters.

aw_list_monitored

List Monitored Endpoints

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.

Takes no parameters.

aw_alerts

Dead Endpoint Alerts

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.

Takes no parameters.

aw_watch

Add Endpoints to Watchlist

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

Parametersurlsrequiredemailrequiredwatch_token

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`.

Takes no parameters.

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`.

Parametersurirequired

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.