An MCP server that lets AI agents run a free Collimer AI-search visibility scan on any website — how visible a brand is in ChatGPT, Perplexity, Google AI Overviews, and other answer engines.

It exposes one tool, beacon_free_scan, which returns a depth-gated teaser: an AI-visibility score, a confidence interval, the single biggest gap, and a branded report URL. The full report (share of voice across each engine + every recommendation) unlocks with a free account on the web.

Install

Claude Desktop / Claude Code (and any MCP client)

Add to your MCP config (e.g. claude_desktop_config.json):

{
  "mcpServers": {
    "collimer": {
      "command": "npx",
      "args": ["-y", "collimer-mcp"]
    }
  }
}

Then ask your assistant something like "How visible is example.com in AI search?" — it will call beacon_free_scan.

The tool

beacon_free_scan(domain, email?)

domain — the website to scan, e.g. example.com or https://example.com.
email (optional) — emails the report and speeds claiming the account later.

Returns the teaser (score, confidence interval, top gap, report URL, and an unlock link). It never returns the full report — that is gated behind a free account.

Configuration (env)

Var	Default	Purpose
`COLLIMER_API_BASE`	`https://app.collimer.com`	API base URL
`COLLIMER_SCAN_SOURCE`	`mcp`	Funnel attribution channel
`COLLIMER_MAX_POLLS`	`60`	Max poll attempts
`COLLIMER_POLL_INTERVAL_MS`	`5000`	Poll interval
`COLLIMER_REQUEST_TIMEOUT_MS`	`30000`	Per-request timeout

Develop

npm install
npm run build          # → dist/
npm run smoke          # real scan against prod, prints the teaser
npm run test:protocol  # spawns the server + calls the tool over MCP/stdio

The public API it wraps is documented at https://app.collimer.com/docs (OpenAPI: /api/v1/openapi.json).