Overview

The Google Analytics MCP Server bridges AI models and analytics by enabling language models to interact directly with Google Analytics 4 data. It's part of the Model Context Protocol (MCP) ecosystem, providing secure, read-only access to your analytics data for natural language queries and AI-powered insights.

Official Server:

Developed and maintained by Google Analytics

Key Features

🗂️

Comprehensive Reporting

Execute custom reports with flexible dimensions, metrics, and date ranges

📊

Real-Time Analytics

Access live user activity and events as they happen on your site

🔐

Secure Read-Only Access

Safe data exploration without risk of modifying your analytics configuration

💬

Natural Language Queries

Ask questions about your data in plain English and get instant insights

Available Tools

Quick Reference

Tool	Purpose	Category
`get_account_summaries`	List GA accounts and properties	Account
`get_property_details`	Get property configuration	Account
`list_google_ads_links`	List linked Google Ads accounts	Integration
`run_report`	Execute custom analytics reports	Reporting
`get_custom_dimensions_and_metrics`	List custom fields	Schema
`run_realtime_report`	Get real-time analytics data	Reporting

Detailed Usage

get_account_summaries�

Retrieves information about your Google Analytics accounts and properties, including property IDs and display names.

use_mcp_tool({
  server_name: "google-analytics",
  tool_name: "get_account_summaries",
  arguments: {}
});

Use this to discover available properties before running reports.

get_property_details�

Returns detailed configuration information for a specific Google Analytics property.

use_mcp_tool({
  server_name: "google-analytics",
  tool_name: "get_property_details",
  arguments: {
    property_name: "properties/123456789"
  }
});

Get timezone, currency, industry category, and other property settings.

run_report�

Execute custom analytics reports with flexible dimensions, metrics, date ranges, and filters.

// Get user and session metrics by country
use_mcp_tool({
  server_name: "google-analytics",
  tool_name: "run_report",
  arguments: {
    property_id: "123456789",
    date_ranges: [{
      start_date: "7daysAgo",
      end_date: "today"
    }],
    dimensions: [{ name: "country" }],
    metrics: [
      { name: "activeUsers" },
      { name: "sessions" }
    ],
    order_bys: [{
      metric: { metric_name: "activeUsers" },
      desc: true
    }],
    limit: 10
  }
});

Supports 200+ dimensions and metrics for comprehensive analysis.

run_realtime_report�

Access real-time analytics data showing current user activity on your site.

// Get current active users by page
use_mcp_tool({
  server_name: "google-analytics",
  tool_name: "run_realtime_report",
  arguments: {
    property_id: "123456789",
    dimensions: [{ name: "unifiedScreenName" }],
    metrics: [{ name: "activeUsers" }],
    limit: 10
  }
});

Data reflects activity from the last 30 minutes.

get_custom_dimensions_and_metrics�

Retrieves all custom dimensions and metrics configured for your property.

use_mcp_tool({
  server_name: "google-analytics",
  tool_name: "get_custom_dimensions_and_metrics",
  arguments: {
    property_name: "properties/123456789"
  }
});

Discover custom fields for use in reports.

list_google_ads_links�

Lists all Google Ads accounts linked to your Analytics property.

use_mcp_tool({
  server_name: "google-analytics",
  tool_name: "list_google_ads_links",
  arguments: {
    property_name: "properties/123456789"
  }
});

View advertising integrations for cross-platform analysis.

Installation

Prerequisites

Before installing, you need to:

Enable required APIs in your Google Cloud Console:
- Google Analytics Admin API
- Google Analytics Data API

Set up Application Default Credentials with the Analytics scope:

gcloud auth application-default login \
  --scopes=https://www.googleapis.com/auth/analytics.readonly

Set environment variables:

export GOOGLE_APPLICATION_CREDENTIALS="/path/to/credentials.json"
export GOOGLE_PROJECT_ID="your-project-id"

Install with pipx

pipx install google-analytics-mcp

Configuration

Add to your MCP settings file (e.g., ~/.gemini/settings.json or Claude Desktop config):

{
  "mcpServers": {
    "google-analytics": {
      "command": "pipx",
      "args": ["run", "google-analytics-mcp"],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/credentials.json",
        "GOOGLE_PROJECT_ID": "your-project-id"
      }
    }
  }
}

Common Use Cases

1. Traffic Analysis

Get insights about website traffic and user behavior:

// Find top pages by users in the last 7 days
use_mcp_tool({
  server_name: "google-analytics",
  tool_name: "run_report",
  arguments: {
    property_id: "123456789",
    date_ranges: [{ start_date: "7daysAgo", end_date: "today" }],
    dimensions: [{ name: "pagePath" }, { name: "pageTitle" }],
    metrics: [
      { name: "activeUsers" },
      { name: "screenPageViews" }
    ],
    order_bys: [{ metric: { metric_name: "activeUsers" }, desc: true }],
    limit: 20
  }
});

2. User Acquisition Sources

Understand where your traffic is coming from:

// Analyze traffic sources and conversion rates
use_mcp_tool({
  server_name: "google-analytics",
  tool_name: "run_report",
  arguments: {
    property_id: "123456789",
    date_ranges: [{ start_date: "30daysAgo", end_date: "today" }],
    dimensions: [
      { name: "sessionSource" },
      { name: "sessionMedium" }
    ],
    metrics: [
      { name: "sessions" },
      { name: "conversions" },
      { name: "engagementRate" }
    ],
    order_bys: [{ metric: { metric_name: "sessions" }, desc: true }]
  }
});

3. Event Tracking

Monitor specific user interactions and events:

// Get most popular events
use_mcp_tool({
  server_name: "google-analytics",
  tool_name: "run_report",
  arguments: {
    property_id: "123456789",
    date_ranges: [{ start_date: "7daysAgo", end_date: "today" }],
    dimensions: [{ name: "eventName" }],
    metrics: [
      { name: "eventCount" },
      { name: "eventCountPerUser" }
    ],
    order_bys: [{ metric: { metric_name: "eventCount" }, desc: true }],
    limit: 25
  }
});

4. Real-Time Monitoring

Watch current activity on your site:

// Monitor active users by device
use_mcp_tool({
  server_name: "google-analytics",
  tool_name: "run_realtime_report",
  arguments: {
    property_id: "123456789",
    dimensions: [{ name: "deviceCategory" }],
    metrics: [{ name: "activeUsers" }]
  }
});

5. Geographic Analysis

See where your users are located:

// Users by country and city
use_mcp_tool({
  server_name: "google-analytics",
  tool_name: "run_report",
  arguments: {
    property_id: "123456789",
    date_ranges: [{ start_date: "30daysAgo", end_date: "today" }],
    dimensions: [
      { name: "country" },
      { name: "city" }
    ],
    metrics: [
      { name: "activeUsers" },
      { name: "averageSessionDuration" }
    ],
    order_bys: [{ metric: { metric_name: "activeUsers" }, desc: true }],
    limit: 50
  }
});

Authentication Setup

Step 1: Create Service Account

Go to Google Cloud Console
Create or select a project
Navigate to IAM & Admin > Service Accounts
Click Create Service Account
Add name and description, click Create
Grant Viewer role, click Continue
Click Done

Step 2: Create Key

Click on the service account you created
Go to Keys tab
Click Add Key > Create new key
Select JSON format
Click Create (the key file will download automatically)

Step 3: Grant Analytics Access

Go to Google Analytics
Navigate to Admin (gear icon)
Under Account or Property, click Account Access Management or Property Access Management
Click + button to add users
Enter your service account email (looks like [email protected])
Assign Viewer role
Click Add

Step 4: Enable APIs

In Google Cloud Console, navigate to APIs & Services > Library
Search for and enable:
- Google Analytics Admin API
- Google Analytics Data API (GA4)

Example Natural Language Queries

Once configured, you can ask questions like:

"What were my top 10 pages by users yesterday?"
"Show me real-time active users by device"
"Which traffic sources drove the most conversions last month?"
"What are my most popular events this week?"
"Compare user engagement between mobile and desktop users"

Sources

Supavec MCP Server: Vector Database for AI Applications

Supavec MCP servers enable AI models to interact with vector databases, providing capabilities for storing, searching, and managing vector embeddings for AI applications.

ArangoDB MCP Server

ArangoDB MCP servers enable AI models to interact with ArangoDB databases, providing capabilities for document operations, graph queries, AQL queries, and multi-model data management.

MongoDB MCP Server

MongoDB MCP servers enable AI models to interact with MongoDB databases and MongoDB Atlas, providing capabilities for document operations, aggregation pipelines, cloud database management, and natural language queries.

Google Analytics MCP Server: AI-Powered Analytics for GA4