CueScout.

See which conversations AI answers actually read about your category, and get into them.

AI clients

CueScout in Hermes Agent

Hermes Agent discovers local stdio MCP tools at startup and prefixes them with the server name. CueScout contributes five diagnostics without an account or API key: visibility, readiness, crawler access, structured data, and sitemap checks. Visibility is one cold search-grounded call; the other four inspect public pages deterministically.

This public diagnostic server is not the CueScout product workspace. It cannot see plans, generated drafts, approvals, exports, GSC or GA4 data, and it cannot publish.

@cuescout/mcp is not on npm yet and the source is not public yet, so there is no way to run the server locally today. The config below is what you will paste when it lands. In the meantime the same five checks are available as public HTTP endpoints that need no account and no key — they are listed with each tool below, and an agent can call them directly.

Where the config lives: ~/.hermes/config.yaml under mcp_servers

Setting it up

  1. 1.Not installable yet

    @cuescout/mcp is not on npm yet and the source is not public yet, so there is no way to run the server locally today. The config below is what you will paste when it lands. In the meantime the same five checks are available as public HTTP endpoints that need no account and no key — they are listed with each tool below, and an agent can call them directly. The tool surface and the endpoints behind it are documented either way, so the direct HTTP call works today.

    What works today

    curl -s https://cuescout.com/api/public/ai-readiness \
  -H 'content-type: application/json' \
  -d '{"url":"https://yoursite.com"}'

  2. 2.Add the server

    Use Hermes' discovery-first command. Its --args option must come last because every following value belongs to the stdio command.

    In a terminal

    hermes mcp add cuescout --command node --args /absolute/path/to/cuescout/services/mcp-public/dist/index.js

  3. 3.Or edit Hermes YAML directly

    Merge this entry into ~/.hermes/config.yaml. Hermes uses mcp_servers with an underscore; a Claude-style mcpServers JSON block is invalid here.

    ~/.hermes/config.yaml

    mcp_servers:
  cuescout:
    command: 'node'
    args: ['/absolute/path/to/cuescout/services/mcp-public/dist/index.js']
    supports_parallel_tool_calls: true

  4. 4.Test discovery and reload

    The test command should discover five tools. In an already-running chat, use /reload-mcp after changing config.

    In a terminal

    hermes mcp test cuescout

What this does not do

  • Free, unauthenticated, and read-only. Only public pages are fetched and no result is stored.
  • Hermes names the tools mcp_cuescout_<tool_name>; that prefix is added by Hermes, not by the server.
  • The visibility result is a cold search-grounded API check, not a logged-in consumer chat and not a trend measured over time.
  • This server cannot access or operate a CueScout workspace.

Frequently asked questions

Why does the example say mcp_servers instead of mcpServers?

Because Hermes config is YAML and its supported root key is mcp_servers. The camel-case JSON key belongs to other MCP clients and Hermes will not treat it as the same setting.

Can Hermes run the five tools concurrently?

Yes. The config opts into parallel calls because every CueScout tool is read-only and each request is independent.

Does this need a CueScout account?

No. The five tools call public endpoints with no authentication — the same ones behind the free tool pages. There is no key to paste and nothing to sign up for.

What does it cost?

Nothing to you. Four of the five tools are HTTP fetches against the site you name. The visibility check puts a real question to a search-grounded engine, which costs us a model call, so it is rate-limited per IP.

Is any of this stored?

No. The public endpoints write nothing to a database. If you want the same checks tracked over time against a site you own, that is the paid product.

Related

AI clients

OpenClaw

Register one read-only stdio server under mcp.servers and expose five public site checks.

AI clients

Claude Code

One `claude mcp add` line, then ask about your site's AI visibility mid-session.

AI clients

Cursor

One block in ~/.cursor/mcp.json, and the agent editing your site can check what engines see of it.

Every integration we publish

Run the checks on your own site

The readiness check is free, needs no signup, and takes about half a minute. It works out what your site is built on and gives you the fixes written for it.

Run the free checkTrack it over time