Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Agent Watch

REMOTE · AGENT-WATCH-API-PRODUCTION.UP.RAILWAY.APP · SCANNED SEP 20

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

−3 this week 69 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security57
Transport & Reachability100
Schema Quality & AI Usability87
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 743 tokens (~82/item across 9 items; 8 tools + 1 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management40
  • Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Agent Watch MCP server?

Agent Watch is a hosted endpoint at https://agent-watch-api-production.up.railway.app/mcp/, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · agent-watch-api-production.up.railway.app

# add to Claude Code
claude mcp add --transport http entradox-agent-watch 'https://agent-watch-api-production.up.railway.app/mcp/'
// .cursor/mcp.json
{
  "mcpServers": {
    "entradox-agent-watch": {
      "url": "https://agent-watch-api-production.up.railway.app/mcp/"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "entradox-agent-watch": {
      "type": "http",
      "url": "https://agent-watch-api-production.up.railway.app/mcp/"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.entradox-agent-watch]
url = "https://agent-watch-api-production.up.railway.app/mcp/"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "entradox-agent-watch": {
      "type": "remote",
      "url": "https://agent-watch-api-production.up.railway.app/mcp/",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add entradox-agent-watch --url 'https://agent-watch-api-production.up.railway.app/mcp/' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  entradox-agent-watch:
    url: "https://agent-watch-api-production.up.railway.app/mcp/"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "entradox-agent-watch": {
      "Transport": "http",
      "Url": "https://agent-watch-api-production.up.railway.app/mcp/"
    }
  }
}
# add to Vellum
assistant mcp add entradox-agent-watch -t streamable-http -u 'https://agent-watch-api-production.up.railway.app/mcp/'
// mcp.json
{
  "mcpServers": {
    "entradox-agent-watch": {
      "type": "http",
      "url": "https://agent-watch-api-production.up.railway.app/mcp/"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 −5
    • Authorization: partial → unverified security
    • Schema quality: 94 → 82 functional
    • Schema quality: unverified → 100 functional
    • New resource “agent-watch” functional
    • New tool “read_skill” functional
    • New tool “skills_list_tool” functional
  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 +1
    • Tool “aw_alerts” rewrote its description, which is the text the model reads security
    • Tool “aw_census” rewrote its description, which is the text the model reads security
    • Tool “aw_check_endpoint” rewrote its description, which is the text the model reads security
    • Tool “aw_list_monitored” rewrote its description, which is the text the model reads security
    • Tool “aw_watch” rewrote its description, which is the text the model reads security
  • 10 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 0
    • Tool “aw_watch” rewrote its description, which is the text the model reads security
    • Stability: unverified → 0.03 functional
    • “aw_watch” added an optional parameter “watch_token” cosmetic
  • 8 Sept 26 +46
    • Authorization: unverified → partial security
    • Injection markers: unverified → pass security
    • Transport: fail → pass security
    • First check of Judged manipulation: pass security
    • Tool coverage: unverified → 100 functional
    • MCP protocol: unverified → pass functional
    • First check of Tool coverage: 0 functional
    • First check of Schema quality: fail functional
    • First check of Schema quality: excellent functional
    • First check of Destructive annotations: pass functional
    • First check of Schema quality: pass functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://agent-watch-api-production.up.railway.app/mcp/

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.up.railway.app CN=YE1,O=Let's Encrypt,C=US 29 Jul 2026 27 Oct 2026 ECDSA 256 ECDSA-SHA384 6da79bb561da3efeb0e751ca21abd3999fe
SANs: *.up.railway.app, up.railway.app
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of agent-watch-api-production.up.railway.app. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
app. present 23684 8 Verified
railway.app. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://agent-watch-api-production.up.railway.app/mcp/ Verified 200
http (plaintext) http://agent-watch-api-production.up.railway.app/mcp/ HTTPS enforced 301 https://agent-watch-api-production.up.railway.app/mcp/
MCP tools · 8 exposed · ~676 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
aw_alerts ~54

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

aw_census ~102

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

aw_check_endpoint ~165

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)

NameTypeReqDescription
timeoutinteger
urlstringyes

No output schema declared.

No examples provided.

aw_health ~37

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

aw_list_monitored ~53

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

aw_watch ~153

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

NameTypeReqDescription
emailstringyes
urlsarrayyes
watch_tokenstring

No output schema declared.

No examples provided.

read_skill ~59

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`.

NameTypeReqDescription
uristringyes

No output schema declared.

No examples provided.

skills_list_tool ~53

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`.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Common questions

What is the Agent Watch MCP server?

Agent Watch is an MCP server listed in the public MCP registry as io.github.entradox/agent-watch. Monitoring for the agent economy, liveness, latency, trust scoring for MCP endpoints. This page covers its hosted endpoint (https://agent-watch-api-production.up.railway.app/mcp/).

Is the Agent Watch MCP server safe to use?

Agent Watch scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Agent Watch MCP server expose?

Agent Watch exposes 8 tools: aw_health, aw_check_endpoint, aw_census, aw_list_monitored, aw_alerts, and 3 more. Their descriptions and schemas cost roughly 676 tokens of context every time the server is loaded.

Does the Agent Watch MCP server require authentication?

No. We connected to Agent Watch without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Agent Watch MCP server still maintained?

Agent Watch is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.