Google Analytics MCP server

Integrates GA4 data to provide web analytics metrics and insights for analyzing website performance and user engagement.
Back to servers
Setup instructions
Provider
Ru Chen Chong
Release date
Nov 29, 2024
Language
TypeScript
Stats
68 stars

The Google Analytics MCP Server provides access to Google Analytics 4 (GA4) data through the Model Context Protocol. It allows you to retrieve analytics metrics like page views, user activity, events, and user behavior through a simple interface.

Prerequisites

  • Node.js 20 or higher
  • A Google Analytics 4 property
  • A Google Cloud project with the Analytics Data API enabled
  • A service account with credentials to access the API

Setup and Configuration

Enable the Google Analytics Data API

  1. Go to the Google Cloud Console
  2. Select your project
  3. Navigate to APIs & Services > Library
  4. Search for "Google Analytics Data API" and enable it

Create a Service Account

  1. In the Google Cloud Console, go to IAM & Admin > Service Accounts
  2. Click "Create Service Account"
  3. Name your service account (e.g., "GA4 MCP Server")
  4. Click "Create and Continue"
  5. Skip granting project access
  6. Click "Done"
  7. Find your new service account and click the three dots under "Actions"
  8. Select "Manage keys", then "Add Key" > "Create new key"
  9. Choose JSON format and click "Create" to download the credentials file

Grant Service Account Access to Google Analytics

  1. Open Google Analytics
  2. Go to the Admin section of your GA4 property
  3. Under the Property column, click Property Access Management
  4. Click the "+" button to add a user
  5. Enter the client_email from your JSON credentials file
  6. Assign the "Viewer" role
  7. Click "Add"

Set Environment Variables

Configure these required environment variables:

  • GOOGLE_CLIENT_EMAIL: The client_email from your service account JSON
  • GOOGLE_PRIVATE_KEY: The private_key from your service account JSON
  • GA_PROPERTY_ID: Your Google Analytics 4 property ID

You can set them in your environment or use a .env file:

export GOOGLE_CLIENT_EMAIL="[email protected]"
export GOOGLE_PRIVATE_KEY="-----BEGIN PRIVATE KEY-----\nYOUR_PRIVATE_KEY\n-----END PRIVATE KEY-----\n"
export GA_PROPERTY_ID="your_property_id"

Installation

Installing via Smithery

To install automatically via Smithery:

npx -y @smithery/cli install mcp-server-google-analytics --client claude

Manual Installation

npm install -g mcp-server-google-analytics

Or use with npx directly:

npx mcp-server-google-analytics

Usage

Starting the Server

pnpm start

Configuration in Claude Desktop

Add this to your Claude Desktop configuration:

{
  "mcpServers": {
    "google-analytics": {
      "command": "npx",
      "args": ["-y", "mcp-server-google-analytics"],
      "env": {
        "GOOGLE_CLIENT_EMAIL": "[email protected]",
        "GOOGLE_PRIVATE_KEY": "your-private-key",
        "GA_PROPERTY_ID": "your-ga4-property-id"
      }
    }
  }
}

Available Functions

runReport

Run a flexible report to get analytics data:

{
  "startDate": "2024-01-01",
  "endDate": "2024-01-31",
  "dimensions": [{ "name": "country" }, { "name": "city" }],
  "metrics": [{ "name": "activeUsers" }, { "name": "newUsers" }],
  "dimensionFilter": {
    "filter": {
      "fieldName": "country",
      "stringFilter": {
        "value": "United States"
      }
    }
  }
}

getPageViews

Get page view metrics for a specific date range:

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

getActiveUsers

Get active users metrics:

{
  "startDate": "2024-01-01",
  "endDate": "2024-01-31"
}

getEvents

Get event metrics:

{
  "startDate": "2024-01-01",
  "endDate": "2024-01-31",
  "eventName": "purchase"
}

getUserBehavior

Get user behavior metrics:

{
  "startDate": "2024-01-01",
  "endDate": "2024-01-31"
}

Security Considerations

  • Least Privilege: Only grant the service account the "Viewer" role in Google Analytics
  • Key Management: Keep your service account key file secure and never expose it in client-side code
  • Environment Variables: Store sensitive information in environment variables, not in code

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "google-analytics" '{"command":"npx","args":["-y","mcp-server-google-analytics"],"env":{"GOOGLE_CLIENT_EMAIL":"[email protected]","GOOGLE_PRIVATE_KEY":"your-private-key","GA_PROPERTY_ID":"your-ga4-property-id"}}'

See the official Claude Code MCP documentation for more details.

For 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 > Tools & Integrations and click "New MCP Server".

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

{
    "mcpServers": {
        "google-analytics": {
            "command": "npx",
            "args": [
                "-y",
                "mcp-server-google-analytics"
            ],
            "env": {
                "GOOGLE_CLIENT_EMAIL": "[email protected]",
                "GOOGLE_PRIVATE_KEY": "your-private-key",
                "GA_PROPERTY_ID": "your-ga4-property-id"
            }
        }
    }
}

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 explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "google-analytics": {
            "command": "npx",
            "args": [
                "-y",
                "mcp-server-google-analytics"
            ],
            "env": {
                "GOOGLE_CLIENT_EMAIL": "[email protected]",
                "GOOGLE_PRIVATE_KEY": "your-private-key",
                "GA_PROPERTY_ID": "your-ga4-property-id"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later