Ganalytics MCP Server

🚀 Google Analytics MCP Server

A Model Context Protocol (MCP) server that provides access to Google Analytics data through tools and services.

Test Results (2024-03-26)

• Total Active Users: 102,883
• Active Users in Belarus: 64,837 (63%)
• Total Page Views: 2,422,925
• Page Views in Belarus: 1,950,160 (80%)

✨ Features

• Access Google Analytics metrics and dimensions via MCP resources.
• Retrieve analytics data with flexible filtering options.
• Obtain formatted data with insights and suggestions.
• Implemented in TypeScript with strong typing.

📦 Installation

1. Clone the repository.
2. Install dependencies:

   npm install
   

3. Create an .env file based on .env.example and add your Google Analytics credentials.
4. Build the project:

   npm run build
   

Set Up Google Analytics Credentials

1. Visit Google Cloud Console.
2. Create a new project or select an existing one.
3. Enable the Google Analytics Data API.
4. Create a service account with appropriate permissions.
5. Download the service account key (JSON format).
6. Extract the client email and private key from the JSON file.
7. Add these to your .env file:

   GA_PROPERTY_ID=your_property_id
   GA_CLIENT_EMAIL=your-service-account@your-project.iam.gserviceaccount.com
   GA_PRIVATE_KEY=-----BEGIN PRIVATE KEY-----\nYourPrivateKeyHere\n-----END PRIVATE KEY-----
   

💻 Usage Examples

Basic Usage

Run the Server

node build/index.js

MCP Configuration

Add the server to your cline_mcp_settings.json file:

{
  "mcpServers": {
    "google-analytics": {
      "command": "node",
      "args": ["/path/to/GAnalytics-MCP-server/build/index.js"],
      "env": {
        "GA_PROPERTY_ID": "your_property_id",
        "GA_CLIENT_EMAIL": "your-service-account@your-project.iam.gserviceaccount.com",
        "GA_PRIVATE_KEY": "-----BEGIN PRIVATE KEY-----\\nYourPrivateKeyHere\\n-----END PRIVATE KEY-----"
      }
    }
  }
}

Advanced Usage

get_analytics_data

Get Google Analytics data with optional filtering and analysis.

Parameters:

• metrics (required): An array of metric names to retrieve.
• dimensions (optional): An array of dimension names.
• startDate (required): The start date in YYYY-MM-DD format.
• endDate (required): The end date in YYYY-MM-DD format.
• filters (optional): An object containing metric and dimension filters.
• orderBy (optional): An array for sorting by fields.
• limit (optional): The number of records to return.
• offset (optional): The index of the first record to return.

Example:

{
  "metrics": ["activeUsers", "newUsers"],
  "dimensions": ["country", "deviceCategory"],
  "startDate": "2024-03-26",
  "endDate": "2024-03-26",
  "filters": {
    "dimensionFilter": {
      "dimension": "country",
      "value": "US"
    }
  },
  "orderBy": ["activeUsers desc"],
  "limit": 10,
  "offset": 0
}

📚 Available Resources

Metrics

• activeUsers: Number of active users.
• newUsers: Number of new users.
• pageviews: Number of page views.
• sessions: Number of sessions.
• bounceRate: Bounce rate.

Dimensions

• country: Country/Region.
• deviceCategory: Device category.
• platform: Platform.
• mobileDeviceModel: Mobile device model.
• os: Operating system.

Development and Testing

To run tests, execute the following command:

npm test

📄 License

[Add license information here]

Contributors

[List contributors here]