Google Analytics

Provides access to GA4 data via MCP with page views, active users, events, and user behavior metrics.

typescript

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-mirror-ruchernchong_mcp-server-google-analytics": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-google-analytics"
      ],
      "env": {
        "GA_PROPERTY_ID": "your-ga4-property-id",
        "GOOGLE_PRIVATE_KEY": "your-private-key",
        "GOOGLE_CLIENT_EMAIL": "your-service-account@project.iam.gserviceaccount.com"
      }
    }
  }
}

You can run this MCP server to access Google Analytics 4 data through the Model Context Protocol SDK. It lets you fetch page views, active users, events, and user behavior metrics over flexible date ranges, making it easy to Power analytics-driven features in your apps.

How to use

You connect to the Google Analytics MCP Server from an MCP client by using a stdio-based configuration. Start the server locally, then issue queries through your client to retrieve page views, active users, events, and user behavior metrics within any date range. Use the server to drive dashboards, reports, or automated insights across your GA4 property.

How to install

Prerequisites: You need Node.js 20 or higher and a GA4 property, plus a Google Cloud project with the Analytics Data API enabled and a service account with access to GA4.

# Install the MCP server package
pnpm install mcp-server-google-analytics

# Start the MCP server (development startup)
pnpm start

# Prepare environment variables for GA4 access
export GOOGLE_CLIENT_EMAIL="your-service-account@project.iam.gserviceaccount.com"
export GOOGLE_PRIVATE_KEY="your-private-key"
export GA_PROPERTY_ID="your-ga4-property-id"

# Example end-to-end setup (local run)
# 1) Install deps
pnpm install mcp-server-google-analytics
# 2) Set env vars (as above)
export GOOGLE_CLIENT_EMAIL="your-service-account@project.iam.gserviceaccount.com"
export GOOGLE_PRIVATE_KEY="your-private-key"
export GA_PROPERTY_ID="your-ga4-property-id"
# 3) Start the server
pnpm start

If you are wiring this into Claude Desktop, use the provided stdio configuration described in the next section.

## Configuration and usage notes

The server is configured to run via a CLI-driven MCP entry. To connect from an MCP client, you can invoke the server through the MCP gateway using the following stdio configuration. This uses npx to launch the package and passes the required environment variables for GA4 access.

{ "name": "google_analytics", "type": "stdio", "command": "npx", "args": ["-y", "mcp-server-google-analytics"], "env": { "GOOGLE_CLIENT_EMAIL": "your-service-account@project.iam.gserviceaccount.com", "GOOGLE_PRIVATE_KEY": "your-private-key", "GA_PROPERTY_ID": "your-ga4-property-id" } }

## Available functions

You can perform the following actions through the MCP server: Get page views, Get active users, Get events, Get user behavior.

{ "startDate": "2024-01-01", "endDate": "2024-01-31", "dimensions": ["page", "country"] }

## Security considerations

Use environment variables for sensitive credentials, apply appropriate CORS settings, grant the service account only the minimum permissions needed, rotate credentials regularly, and monitor API usage with rate limiting if necessary.

## Contributing

Contributions are welcome. Follow the project’s contributing guidelines for submitting changes and adhering to the code of conduct.

## License

This project is licensed under the MIT License.

## Available tools

### getPageViews

Fetch page view metrics for a specified date range with optional dimensions such as page and country.

### getActiveUsers

Retrieve active user counts over a given date span.

### getEvents

Query event metrics, with optional filtering by event name.

### getUserBehavior

Obtain user behavior metrics like session duration and bounce rate across a date range.

Built by

VeilStrat

AI signals for GTM teams