CueScout.

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

AI clients

CueScout in OpenClaw

OpenClaw can launch local stdio MCP servers and make their tools available to its runtimes. CueScout adds five narrow diagnostics: one cold search-grounded visibility query and four deterministic checks against public pages.

This is not a connection to your CueScout workspace. It cannot read your weekly plan, drafts, Search Console or Analytics data, approve work, export pages, or publish anything.

@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: openclaw.json under mcp.servers, or the `openclaw mcp add` command

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.Register CueScout and probe it

    OpenClaw keeps managed MCP definitions under mcp.servers. The add command probes the process and lists its tools before saving it; --parallel marks these independent read-only calls safe to run concurrently.

    In a terminal

    openclaw mcp add cuescout --command node --arg /absolute/path/to/cuescout/services/mcp-public/dist/index.js --parallel

  3. 3.Or add the native config directly

    Merge this mcp block into openclaw.json. It is OpenClaw's mcp.servers shape, not the mcpServers block used by Claude clients.

    openclaw.json

    {
  "mcp": {
    "servers": {
      "cuescout": {
        "command": "node",
        "args": [
          "/absolute/path/to/cuescout/services/mcp-public/dist/index.js"
        ],
        "supportsParallelToolCalls": true
      }
    }
  }
}

  4. 4.Verify all five tools

    Run a probe, then ask OpenClaw to list the CueScout tools. You should see visibility, readiness, crawler access, structured data, and sitemap checks.

    In a terminal

    openclaw mcp probe cuescout --json

What this does not do

  • Free, unauthenticated, and read-only. The server only checks public URLs and writes nothing.
  • Visibility is one cold search-grounded API query, without consumer-app memory, personalization, or location. It is one datapoint, not an overall visibility score.
  • This server has no CueScout workspace access and does not complete an autonomous monitoring or publishing loop.

Frequently asked questions

Can OpenClaw run these checks on a schedule?

OpenClaw can schedule work that calls the tools, but this server itself stores no schedule or history. Each invocation is a fresh public check.

Why enable parallel tool calls?

All five tools are independent and read-only, so OpenClaw may safely run separate checks concurrently when the workflow benefits from it.

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

Hermes Agent

Add CueScout under mcp_servers in config.yaml, then discover five read-only public tools.

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