Google Analytics MCP Server

Google Analytics MCP Server

What is Google Analytics MCP Server about?

Google Analytics MCP Server bridges Google Analytics 4 with MCP‑compatible AI assistants, enabling users to query website traffic, user behavior, and e‑commerce data in plain English. It taps into more than 200 GA4 dimensions and metrics, handling aggregation and row‑volume optimization automatically.

How to use Google Analytics MCP Server?

1. Prepare credentials – create a service‑account in Google Cloud, enable the Google Analytics Data API, download the JSON key, and grant the service account Viewer access to the GA4 property.
2. Install the server – either pip install google-analytics-mcp (recommended) or clone the repo and install the requirements.
3. Configure MCP – add a server entry pointing to the Python module (ga4_mcp_server) and set the environment variables GOOGLE_APPLICATION_CREDENTIALS and GA4_PROPERTY_ID.
4. Ask questions – use any MCP client (Claude, Cursor, etc.) and phrase queries like “Show me revenue by country for the last 30 days”.

Key features of Google Analytics MCP Server

• 200+ GA4 dimensions & metrics exposed through natural language.
• Smart data‑volume management with row‑estimation, warnings, and automatic aggregation.
• Built‑in tools: get_ga4_data, list_dimension_categories, list_metric_categories, get_dimensions_by_category, get_metrics_by_category.
• User‑controlled parameters – limit, proceed_with_large_dataset, enable_aggregation, estimate_only.
• Cross‑client compatibility – works with Claude, Cursor and any MCP‑compatible service.

Use cases of Google Analytics MCP Server

• Traffic analysis – quickly retrieve visits, sessions, bounce rate by geography or device.
• E‑commerce reporting – identify top‑selling products, conversion rates, revenue attribution.
• Marketing performance – compare source/medium performance across time periods.
• Content optimization – rank pages by engagement rate and monitor trends.
• Ad‑hoc data exploration – non‑technical users can ask ad‑hoc questions without writing GA4 queries.

FAQ from the Google Analytics MCP Server

Q: Which Python version is required? A: Python 3.10 or higher.

Q: Do I need a Google Cloud project? A: Yes – a service account with the Analytics Data API enabled and Viewer access to the GA4 property.

Q: How do I avoid context‑window crashes? A: The server automatically estimates row counts and suggests aggregations; you can also set limit or proceed_with_large_dataset.

Q: Can I use the server with other MCP clients? A: Any client that follows the MCP protocol can connect, not just Claude or Cursor.

Q: What if I receive credential errors? A: Verify the JSON key path, ensure the service account email is added to GA4 Property access, and confirm you are using the numeric Property ID (not the Measurement ID).

Google Analytics MCP Server

Connect Google Analytics 4 data to Claude, Cursor and other MCP clients. Query your website traffic, user behavior, and analytics data in natural language with access to 200+ GA4 dimensions and metrics.

Compatible with: Claude, Cursor and other MCP clients.

I also built a Google Search Console MCP that enables you to mix & match the data from both the sources

Prerequisites

Check your Python setup:

# Check Python version (need 3.10+)
python --version
python3 --version

# Check pip
pip --version
pip3 --version

Required:

• Python 3.10 or higher
• Google Analytics 4 property with data
• Service account with Analytics Reporting API access

---

Step 1: Setup Google Analytics Credentials

Create Service Account in Google Cloud Console

1. Go to Google Cloud Console
2. Create or select a project:
   • New project: Click "New Project" → Enter project name → Create
   • Existing project: Select from dropdown
3. Enable the Analytics APIs:
   • Go to "APIs & Services" → "Library"
   • Search for "Google Analytics Data API" → Click "Enable"
4. Create Service Account:
   • Go to "APIs & Services" → "Credentials"
   • Click "Create Credentials" → "Service Account"
   • Enter name (e.g., "ga4-mcp-server")
   • Click "Create and Continue"
   • Skip role assignment → Click "Done"
5. Download JSON Key:
   • Click your service account
   • Go to "Keys" tab → "Add Key" → "Create New Key"
   • Select "JSON" → Click "Create"
   • Save the JSON file - you'll need its path

Add Service Account to GA4

1. Get service account email:
   • Open the JSON file
   • Find the client_email field
   • Copy the email (format: ga4-mcp-server@your-project.iam.gserviceaccount.com)
2. Add to GA4 property:
   • Go to Google Analytics
   • Select your GA4 property
   • Click "Admin" (gear icon at bottom left)
   • Under "Property" → Click "Property access management"
   • Click "+" → "Add users"
   • Paste the service account email
   • Select "Viewer" role
   • Uncheck "Notify new users by email"
   • Click "Add"

Find Your GA4 Property ID

1. In Google Analytics, select your property
2. Click "Admin" (gear icon)
3. Under "Property" → Click "Property details"
4. Copy the Property ID (numeric, e.g., 123456789)
   • Note: This is different from the "Measurement ID" (starts with G-)

Test Your Setup (Optional)

Verify your credentials:

pip install google-analytics-data

Create a test script (test_ga4.py):

import os
from google.analytics.data_v1beta import BetaAnalyticsDataClient

# Set credentials path
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "/path/to/your/service-account-key.json"

# Test connection
client = BetaAnalyticsDataClient()
print("✅ GA4 credentials working!")

Run the test:

python test_ga4.py

If you see "✅ GA4 credentials working!" you're ready to proceed.

---

Step 2: Install the MCP Server

Choose one method:

Method A: pip install (Recommended)

pip install google-analytics-mcp

MCP Configuration:

First, check your Python command:

python3 --version
python --version

Then use the appropriate configuration:

If python3 --version worked:

{
  "mcpServers": {
    "ga4-analytics": {
      "command": "python3",
      "args": ["-m", "ga4_mcp_server"],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/your/service-account-key.json",
        "GA4_PROPERTY_ID": "123456789"
      }
    }
  }
}

If python --version worked:

{
  "mcpServers": {
    "ga4-analytics": {
      "command": "python",
      "args": ["-m", "ga4_mcp_server"],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/your/service-account-key.json",
        "GA4_PROPERTY_ID": "123456789"
      }
    }
  }
}

Method B: GitHub download

git clone https://github.com/surendranb/google-analytics-mcp.git
cd google-analytics-mcp
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

MCP Configuration:

{
  "mcpServers": {
    "ga4-analytics": {
      "command": "/full/path/to/ga4-mcp-server/venv/bin/python",
      "args": ["/full/path/to/ga4-mcp-server/ga4_mcp_server.py"],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/your/service-account-key.json",
        "GA4_PROPERTY_ID": "123456789"
      }
    }
  }
}

---

Step 3: Update Configuration

Replace these placeholders in your MCP configuration:

• /path/to/your/service-account-key.json with your JSON file path
• 123456789 with your GA4 Property ID
• /full/path/to/ga4-mcp-server/ with your download path (Method B only)

---

Usage

Once configured, ask your MCP client questions like:

Discovery & Exploration

• What GA4 dimension categories are available?
• Show me all ecommerce metrics
• What dimensions can I use for geographic analysis?

Traffic Analysis

• What's my website traffic for the past week?
• Show me user metrics by city for last month
• Compare bounce rates between different date ranges

Multi-Dimensional Analysis

• Show me revenue by country and device category for last 30 days
• Analyze sessions and conversions by campaign and source/medium
• Compare user engagement across different page paths and traffic sources

E-commerce Analysis

• What are my top-performing products by revenue?
• Show me conversion rates by traffic source and device type
• Analyze purchase behavior by user demographics

---

Quick Start Examples

Try these example queries to see the MCP's analytical capabilities:

1. Geographic Distribution

Show me a map of visitors by city for the last 30 days, with a breakdown of new vs returning users

This demonstrates:

• Geographic analysis
• User segmentation
• Time-based filtering
• Data visualization

2. User Behavior Analysis

Compare average session duration and pages per session by device category and browser over the last 90 days

This demonstrates:

• Multi-dimensional analysis
• Time series comparison
• User engagement metrics
• Technology segmentation

3. Traffic Source Performance

Show me conversion rates and revenue by traffic source and campaign, comparing last 30 days vs previous 30 days

This demonstrates:

• Marketing performance analysis
• Period-over-period comparison
• Conversion tracking
• Revenue attribution

4. Content Performance

What are my top 10 pages by engagement rate, and how has their performance changed over the last 3 months?

This demonstrates:

• Content analysis
• Trend analysis
• Engagement metrics
• Ranking and sorting

---

🚀 Performance Optimizations

This MCP server includes built-in optimizations to prevent context window crashes and ensure smooth operation:

Smart Data Volume Management

• Automatic row estimation - Checks data volume before fetching
• Interactive warnings - Alerts when queries would return >2,500 rows
• Optimization suggestions - Provides specific recommendations to reduce data volume

Server-Side Processing

• Intelligent aggregation - Automatically aggregates data when beneficial (e.g., totals across time periods)
• Smart sorting - Returns most relevant data first (recent dates, highest values)
• Efficient filtering - Leverages GA4's server-side filtering capabilities

User Control Parameters

• limit - Set maximum number of rows to return
• proceed_with_large_dataset=True - Override warnings for large datasets
• enable_aggregation=False - Disable automatic aggregation
• estimate_only=True - Get row count estimates without fetching data

Example: Handling Large Datasets

# This query would normally return 2,605 rows and crash context window
get_ga4_data(
    dimensions=["date", "pagePath", "country"],
    date_range_start="90daysAgo"
)
# Returns: {"warning": True, "estimated_rows": 2605, "suggestions": [...]}

# Use monthly aggregation instead
get_ga4_data(
    dimensions=["month", "pagePath", "country"], 
    date_range_start="90daysAgo"
)
# Returns: Clean monthly data with manageable row count

---

Available Tools

The server provides 5 main tools with built-in optimization to prevent context window crashes:

1. get_ga4_data - Retrieve GA4 data with custom dimensions and metrics
   • Smart data volume warnings - Alerts when queries would return >2,500 rows
   • Server-side aggregation - Automatically aggregates data when beneficial
   • Intelligent sorting - Returns most relevant data first
   • User control parameters - limit, proceed_with_large_dataset, enable_aggregation
2. list_dimension_categories - Browse available dimension categories
3. list_metric_categories - Browse available metric categories
4. get_dimensions_by_category - Get dimensions for a specific category
5. get_metrics_by_category - Get metrics for a specific category

---

Dimensions & Metrics

Access to 200+ GA4 dimensions and metrics organized by category:

Dimension Categories

• Time: date, hour, month, year, etc.
• Geography: country, city, region
• Technology: browser, device, operating system
• Traffic Source: campaign, source, medium, channel groups
• Content: page paths, titles, content groups
• E-commerce: item details, transaction info
• User Demographics: age, gender, language
• Google Ads: campaign, ad group, keyword data
• And 10+ more categories

Metric Categories

• User Metrics: totalUsers, newUsers, activeUsers
• Session Metrics: sessions, bounceRate, engagementRate
• E-commerce: totalRevenue, transactions, conversions
• Events: eventCount, conversions, event values
• Advertising: adRevenue, returnOnAdSpend
• And more specialized metrics

---

Troubleshooting

If you get "No module named ga4_mcp_server" (Method A):

pip3 install --user google-analytics-mcp

If you get "executable file not found":

• Try the other Python command (python vs python3)
• Use pip3 instead of pip if needed

Permission errors:

# Try user install instead of system-wide
pip install --user google-analytics-mcp

Credentials not working:

1. Verify the JSON file path is correct and accessible
2. Check service account permissions:
   • Go to Google Cloud Console → IAM & Admin → IAM
   • Find your service account → Check permissions
3. Verify GA4 access:
   • GA4 → Admin → Property access management
   • Check for your service account email
4. Verify ID type:
   • Property ID: numeric (e.g., 123456789) ✅
   • Measurement ID: starts with G- (e.g., G-XXXXXXXXXX) ❌

API quota/rate limit errors:

• GA4 has daily quotas and rate limits
• Try reducing the date range in your queries
• Wait a few minutes between large requests

---

Project Structure

google-analytics-mcp/
├── ga4_mcp_server.py       # Main MCP server
├── ga4_dimensions.json     # All available GA4 dimensions
├── ga4_metrics.json        # All available GA4 metrics
├── requirements.txt        # Python dependencies
├── pyproject.toml          # Package configuration
├── README.md               # This file
└── claude-config-template.json  # MCP configuration template

---

License

MIT License