Skip to main content
Glama
Privatus-Analytics

Privatus Analytics MCP server

Official

Privatus Analytics MCP server

Ask your AI assistant how your website is doing, and get real numbers back.

You want to know which page brought the most visitors last week, or if your site is down. Normally you open a dashboard, click through menus and copy numbers into a chat. With this server, your assistant reads your website stats for you. You just ask.

Privatus Analytics counts visits without cookies, so your site needs no cookie pop-up for its analytics, and bots are filtered out. This hosted MCP server lets Cline, Claude, ChatGPT, Cursor and VS Code read those stats and manage goals, alerts and uptime checks.

Free plan, no card: 10,000 events a month on up to 3 sites. Start free at privatusanalytics.com.

There is nothing to install. The server is hosted at:

https://privatusanalytics.com/mcp

1. Get an API token

  1. Sign in at privatusanalytics.com (or make a free account).

  2. Open Workspace settings, then API tokens, and create a token. It starts with pat_.

  3. For reports only, give it just the analytics.read permission. A smaller token is safer.

Related MCP server: Google MCP Server

2. Add it to Cline

Open Cline, click MCP Servers, then Configure MCP Servers, and add this to cline_mcp_settings.json:

{
  "mcpServers": {
    "privatus-analytics": {
      "type": "streamableHttp",
      "url": "https://privatusanalytics.com/mcp",
      "headers": {
        "Authorization": "Bearer pat_YOUR_TOKEN"
      }
    }
  }
}

Replace pat_YOUR_TOKEN with your token and save. The server shows a green dot when it is connected.

Other clients

  • Claude Desktop: Settings, Connectors, Add custom connector, enter https://privatusanalytics.com/mcp and sign in. No token needed (OAuth).

  • Claude Code: claude mcp add --transport http privatus https://privatusanalytics.com/mcp --header "Authorization: Bearer pat_YOUR_TOKEN"

  • ChatGPT, Cursor, VS Code, Gemini CLI: see the client setup guide.

Install with mpak

Some apps can only start a local program. They cannot connect to a web address. For those, this repo has a tiny bridge program, published on mpak.dev as @privatus-analytics/mcp-server. It needs Node.js 18 or newer and has no other parts to install.

mpak bundle pull @privatus-analytics/mcp-server

When it asks for your API token, paste the pat_ token from step 1. The bridge sends each request to https://privatusanalytics.com/mcp and passes the reply back. It keeps no data and reads no files.

You can also run it by hand:

PRIVATUS_API_TOKEN=pat_YOUR_TOKEN node server/index.js

Run the tests with npm test.

Things to ask

  • "Which pages got the most visitors last month?"

  • "Where did my traffic come from this week, compared with last week?"

  • "Are any of my uptime checks down right now?"

  • "Create a goal for visits to /thank-you."

Safety

  • Each tool checks your token's permissions, and the server only shows tools your token may use.

  • Hard-to-undo actions (deleting data, billing, access settings, tokens) are never done by the assistant. You get a link to do them yourself.

  • No tool takes a password or a token as input.

Full docs: privatusanalytics.com/docs/mcp

License

MIT, Two Phase LLC. See LICENSE.

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    Privacy friendly, cookieless web analytics built MCP-first. "Add analytics to my Next.js app" → an AI agent runs the setup_analytics_for_site tool, picks the right install snippet, edits your layout file, and verifies the script is loading. OAuth onboarding, no API keys to paste.
    28
    85 npm
    1
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    A unified MCP server that gives AI assistants direct access to Google Analytics 4, Google Search Console, Google Ads and Google Merchant Center data using OAuth2 user credentials.
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Enables MCP clients such as Claude, Codex, and Cursor to read projects, monitors, captured AI answers, account/plan usage, and AI-referral analytics, and to set up projects, monitors, goals, and analytics properties. It also supports checking tracking-snippet verification, with monitor creation starting metered runs that consume credits.
    20
    36 npm
    MIT