Google Analytics MCP server

This MCP server provides an interface to access the Google Analytics Data API through the Model Context Protocol, allowing you to retrieve analytics data and reports from your GA4 properties.

Features

The MCP server provides tools and resources for accessing key Google Analytics Data API functionality:

Tools

• get_report: Retrieves reports based on specified date ranges, metrics, and dimensions
• get_realtime_data: Fetches real-time analytics data

Resources

• ga4://property/{propertyId}/metadata: Accesses metadata for Google Analytics properties

Installation

Prerequisites

1. Create a Google Cloud project and enable the Analytics Data API
2. Create a service account and download the credentials JSON file
3. Grant the service account appropriate access to your GA4 property

Setup

# Clone the repository
git clone https://github.com/eno-graph/mcp-server-google-analytics.git
cd mcp-server-google-analytics

# Install dependencies
npm install

# Build
npm run build

Configure Environment Variables

You'll need to set the following environment variables:

export GOOGLE_CLIENT_EMAIL="[email protected]"
export GOOGLE_PRIVATE_KEY="your-private-key"
export GA_PROPERTY_ID="your-ga4-property-id"

Usage

Starting the Server

Start the MCP server with:

npm start

Or use the provided script:

./run-server.sh

Claude Desktop Configuration

Add the following to your Claude Desktop configuration file:

{
  "mcpServers": {
    "google-analytics": {
      "command": "node",
      "args": ["/path/to/mcp-server-google-analytics/build/index.js"],
      "env": {
        "GOOGLE_CLIENT_EMAIL": "[email protected]",
        "GOOGLE_PRIVATE_KEY": "your-private-key",
        "GA_PROPERTY_ID": "your-ga4-property-id"
      }
    }
  }
}

Using the Tools

Getting Reports

Use the get_report tool to retrieve analytics data for a specific time period:

get_report tool with the following arguments:
{
  "startDate": "7daysAgo",
  "endDate": "today",
  "metrics": ["activeUsers", "screenPageViews"],
  "dimensions": ["date"],
  "limit": 10
}

Fetching Real-time Data

Use the get_realtime_data tool to access current activity:

get_realtime_data tool with the following arguments:
{
  "metrics": ["activeUsers"],
  "dimensions": ["deviceCategory"],
  "limit": 10
}

Accessing Resources

To explore available metrics and dimensions for your GA4 property:

Access the resource: ga4://property/123456789/metadata

Replace 123456789 with your actual GA4 property ID to view its metadata.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

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

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.