For AI agents

FrontStat MCP server

Ask your AI agent whether ChatGPT, Claude and Gemini recommend your product, right from Claude Code, Cursor or Claude Desktop.

Anyone can check a launch FrontStat tracks. With FrontStat Pro, your agent also reads your daily report: your buyer questions, who wins instead of you, the sites AI search engines cite, and your score over 30 days.

Endpoint

https://frontstat.com/api/mcp

For the Pro tools, send your private dashboard token as Authorization: Bearer <token>. The token is the 48 characters at the end of your dashboard link (frontstat.com/d/<token>). Keep it private: it opens your dashboard. Without a token, only check_public_launch answers.

Claude Code

One command in your terminal:

claude mcp add --transport http frontstat https://frontstat.com/api/mcp --header "Authorization: Bearer <your dashboard token>"

Cursor

Add this to ~/.cursor/mcp.json, or .cursor/mcp.json in your project:

{
  "mcpServers": {
    "frontstat": {
      "url": "https://frontstat.com/api/mcp",
      "headers": {
        "Authorization": "Bearer <your dashboard token>"
      }
    }
  }
}

Claude Desktop

Add this to claude_desktop_config.json (Settings, Developer, Edit Config), then restart Claude Desktop:

{
  "mcpServers": {
    "frontstat": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://frontstat.com/api/mcp",
        "--header",
        "Authorization:Bearer <your dashboard token>"
      ]
    }
  }
}

Tools

• check_public_launchFree

  Look up a product launch that FrontStat already tracks: its name, its rank on this week's or this month's launch board, its visibility score (0 to 100), and whether ChatGPT, Claude and Gemini recommend it for its buyer question, with the products they name instead. Returns a link to its public FrontStat page. If FrontStat does not track the domain yet, says so and links to the free report. No token needed.

• get_visibilityPro

  Your latest FrontStat Pro report: date, visibility score, whether each AI search engine recommends your product for your main buyer question and who it names instead, and for your buyer questions how many answers recommend you (X of Y) per assistant.

• list_buyer_questionsPro

  Each buyer question FrontStat asks the AI search engines about your market, with yes or no per engine: does the answer recommend your product.

• who_wins_insteadPro

  The products the AI search engines name instead of yours, and the sites they cite, each with how many answers it appears in, from your latest Pro report.

• cited_sitesPro

  The sites the AI search engines cite most when they answer your buyer questions, with how many answers cite each one, your own domain left out. These are the pages to get mentioned on.

• visibility_historyPro

  One point per day for the last 30 days: your visibility score and how many answers recommend your product. Use it to see whether your changes moved AI search engines.

Limit: 120 calls per hour. Data refreshes once a day, so one call a day per tool is plenty.