Skip to content

AI clients

CueScout in Cursor

Cursor is the client where these tools pay off fastest, because the agent that reads the finding is the one that can act on it. "The structured data check says sameAs is empty" is a sentence Cursor can turn into a diff without you switching context.

Where the config lives
~/.cursor/mcp.json for every project, or .cursor/mcp.json inside one

By Telman Gadimov · Updated

What it does

Runs @cuescout/mcp through npx, so there is nothing to install first.

Setting it up

3 steps, and the last one proves it works.

  1. Pick the scope

    ~/.cursor/mcp.json makes the server available in every project. .cursor/mcp.json inside a project keeps it to that one and travels with the repo. For a tool you will use on one site, the project file is the tidier choice.

  2. Add the server block

    Cursor uses the same mcpServers shape as the rest of the ecosystem, so this block is identical to the Claude Desktop one.

    ~/.cursor/mcp.json

    {
  "mcpServers": {
    "cuescout": {
      "command": "npx",
      "args": ["-y", "@cuescout/mcp"]
    }
  }
}

  3. Enable it in Settings → MCP

    New servers show up in that panel with a toggle. A green dot and five tools means it started; a red one is usually a path that is not absolute.

What this does not do

  • The tools read your deployed site, not your working tree. A fix you have not shipped will not change the answer.
  • Public pages only — nothing behind a login.
  • No history. The check tells you the state now.

Questions

Why does the check still fail after the agent fixed the code?

Because the tool fetched your live site. Every one of these runs against a URL over HTTP, so nothing changes until the fix is deployed.

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?

Each run keeps a short record: what you entered, a summary of the result, the time and your IP address, so the daily limits can be enforced. The privacy policy has the details. Nothing is added to a CueScout account. If you want the same checks tracked over time against a site you own, that is the paid product.

Related

WindsurfOne block in mcp_config.json and Cascade can check what the engines see of your site.VS CodeA .vscode/mcp.json block — note the key is `servers`, not `mcpServers`.Claude CodeOne `claude mcp add` line, then ask about your site's AI visibility mid-session.
All integrations

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 check Track it over time