Skip to content

Agent Watch MCP server

io.github.entradox/agent-watchentradoxstreamable-httpv0.1.0Scanned

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

8 tools: 4 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 4 write, 4 read.
  • Reads private data · 1
  • Reads text others write · 1
  • Can send data out · 3
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

4 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Agent Watch MCP server can do

The Agent Watch MCP server is published by the GitHub account entradox. It has 8 tools. It can create or change data (4 tools: aw_health, aw_check_endpoint, aw_census and aw_watch), but cannot delete data. 4 tools only read.

1 tool reads private data (read_skill); 1 tool brings in text other people can write (read_skill); 3 tools can send data out of your system (aw_check_endpoint, aw_watch and read_skill). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 19, 2026, version 0.1.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

8 tools

Changes things 4Claude Code: ask
  • aw_censusFull-census summary of the official MCP registry: 7,454 endpoints probed with real MCP handshakes.1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...directing — liveness unprovable without credentials. Use to quantify how much of the MC..."

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Registry Liveness Census
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • aw_check_endpointProbe an MCP or HTTP-402 endpoint now and get its trust verdict.Can send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    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)

    Annotations the server declares

    • title: Probe MCP Endpoint
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • aw_healthLiveness check for the Agent Watch API.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Liveness check for the Agent Watch API. Returns ok, service name, and version. Call this first to verify connectivity before using other tools.

    Annotations the server declares

    • title: Agent Watch Health
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • aw_watchAdd endpoints to your personal watchlist (probed immediately, then every 6h).Can send data outNo findings

    Why it is in this group

    • The description's first verb is "add": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    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

    Annotations the server declares

    • title: Add Endpoints to Watchlist
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
Only reads 4Show 4 read-only tools
  • aw_alertsShow dead endpoints across the monitored registry (alive=false).No findings

    Why it is in this group

    • The description's first verb is "show": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Dead Endpoint Alerts
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • aw_list_monitoredList all endpoints in the Agent Watch census with their registry names.No findings

    Why it is in this group

    • The name "aw_list_monitored" says "list": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: List Monitored Endpoints
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • read_skillRead a product skill file by its skill:// URI.Reads private dataReads text others writeCan send data outNo findings

    Why it is in this group

    • The name "read_skill" says "read": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "read" and "file": it reads files.
    • untrusted-inputThe description's first sentence says "read" and "uri": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.uri), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.uri): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    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`.
  • skills_list_toolList this product's skills.No findings

    Why it is in this group

    • The name "skills_list_tool" says "list": a word for reading.
    Description, as the server wrote it
    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`.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

3 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 untrusted-input tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out3
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__agent-watch__read_skill"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:04 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
4
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://agent-watch-api-production.up.railway.app/mcp/: tools/list returned 8 tools to an anonymous client, including aw_health (write), aw_check_endpoint (write), aw_census (write), aw_watch (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 info
  • The description mentions "credentials".

    Matched text

    description: "...directing — liveness unprovable without credentials. Use to quantify how much of the MC..."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-watch https://agent-watch-api-production.up.railway.app/mcp/
claude mcp add --transport http agent-watch https://agent-watch-api-production.up.railway.app/mcp/

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agent-watch__aw_list_monitored",
      "mcp__agent-watch__aw_alerts",
      "mcp__agent-watch__skills_list_tool"
    ],
    "ask": [
      "mcp__agent-watch__aw_health",
      "mcp__agent-watch__aw_check_endpoint",
      "mcp__agent-watch__aw_census",
      "mcp__agent-watch__aw_watch",
      "mcp__agent-watch__read_skill"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agent-watch. Review it before you use it.

Capability tags behind 3 rules
  • mcp__agent-watch__aw_check_endpoint outbound
  • mcp__agent-watch__aw_watch outbound
  • mcp__agent-watch__read_skill private-data, untrusted-input, outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.entradox/agent-watch/verify?hash=4e3671d18c65ccb03ccea08fddef97dd15b5943a0c3af1be05de938a1f5aac56" | jq -e '.changed == false'

Pinned hash 4e3671d18c65, from Nov 19, 2026, 16:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.entradox/agent-watch/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.entradox/agent-watch
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.entradox/agent-watch.svg)](https://radar.anlyon.com/servers/io.github.entradox/agent-watch)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:33 UTC.

Agent Watch MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Agent Watch MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 4 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Agent Watch MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Agent Watch MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Agent Watch MCP server have?

8 tools: 4 write, 4 read. aw_health, aw_check_endpoint, aw_census, aw_watch, aw_list_monitored, aw_alerts, skills_list_tool and read_skill.

Does the Agent Watch MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Agent Watch MCP server send data to outside services?

3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): aw_check_endpoint, aw_watch and read_skill.

Has the Agent Watch MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.