Wardn HubTrusted MCP server directory.

Registry

  • MCP Servers
  • Skills
  • Categories

Resources

  • API docs
  • Score method

Contribute

  • Submit server
  • Advertise
Ā© 2026 Wardn Hub
Wardn Hub
MCP ServersSkillsCategoriesAPI docsSubmit server
Submit server

Google Analytics 4 MCP Server

io.github.surendranb/google-analytics-mcp

Source

Documentation

Google Analytics MCP Logo

Google Analytics 4 MCP Server

mcp-name: io.github.surendranb/google-analytics-mcp

PyPI version Python Versions GitHub Actions CI GitHub stars License: Apache 2.0

Connect Google Analytics 4 data directly to AI agents, analyst copilots, and MCP runtimes across Claude, ChatGPT, Gemini, Cursor, VS Code, and OpenClaw. Gives models analysis-ready GA4 access with live schema discovery, metric auto-aliasing, server-side aggregation, and autonomous self-healing defenses.

🌐 Website & Documentation: https://ga4mcp.com
šŸ”— Sister Project: Google Search Console MCP

PyPI Downloads Breakdown and Trend


⚔ Quickstart — 1-Line Installations

1. Universal 1-Line Installer (Recommended)

Auto-detects your system, configures Gemini CLI, Claude Desktop, Cursor, and VS Code automatically in 1 command:

curl -fsSL https://ga4.builditwithai.xyz | bash

2. Homebrew (macOS & Linux)

brew tap surendranb/tap
brew install google-analytics-mcp

3. One-Click for Cursor

Add to Cursor

4. NPX / Node.js (Claude Code, Cursor, VS Code, Windsurf)

Add to your MCP configuration file (claude_desktop_config.json or .cursor/mcp.json):

{
  "mcpServers": {
    "ga4-analytics": {
      "command": "npx",
      "args": ["-y", "google-analytics-mcp"],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/absolute/path/to/service-account-key.json",
        "GA4_PROPERTY_ID": "123456789"
      }
    }
  }
}

5. Gemini CLI Extension

Install directly into Google Gemini CLI with a single command:

gemini extensions install github.com/surendranb/google-analytics-mcp

6. Python uvx & Explicit python -m ga4_mcp

{
  "mcpServers": {
    "ga4-analytics": {
      "command": "uvx",
      "args": ["--from", "google-analytics-mcp", "ga4-mcp-server"],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/absolute/path/to/service-account-key.json",
        "GA4_PROPERTY_ID": "123456789"
      }
    }
  }
}

Or run directly via ga4-mcp-server / python -m ga4_mcp:

{
  "mcpServers": {
    "ga4-analytics": {
      "command": "python",
      "args": ["-m", "ga4_mcp"],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/absolute/path/to/service-account-key.json",
        "GA4_PROPERTY_ID": "123456789"
      }
    }
  }
}

🧠 Why AI Agents & Marketers Prefer This Server

  • Autonomous Self-Healing: System directives automatically intercept schema hallucinations (like guessing legacy metric names or incorrect filter nesting) and guide models to self-correct via get_troubleshooting_guide.
  • Metric Auto-Aliasing: Automatically maps legacy or common LLM requests like 'conversions' → 'keyEvents', preventing unnecessary query failures.
  • Server-Side Aggregation: Computes property totals dynamically for non-time-series queries, so LLMs spend time answering business questions rather than parsing raw rows.
  • Data Volume Protection: Runs quick row-count estimates before executing large queries (>2,500 rows) to prevent crashing model context windows.
  • Multi-Platform Support: Native packages and manifests for PyPI, npm, Gemini CLI, Smithery, OpenClaw, and OpenAPI REST actions.

šŸ”‘ Setup & Credentials Guide

1. Create a Google Cloud Service Account

  1. Open the Google Cloud Console.
  2. Enable the Google Analytics Data API.
  3. Under APIs & Services → Credentials, create a Service Account.
  4. Create a JSON Key and save it locally on your machine (e.g. /Users/yourname/keys/ga4-key.json).

2. Grant Viewer Access in GA4

  1. Open Google Analytics.
  2. Select your GA4 Property → Open Admin (gear icon) → Property Access Management.
  3. Add the Service Account email (found inside the JSON key as client_email) with the Viewer role.

3. Find Your GA4 Property ID

  1. In Google Analytics Admin → Property Details.
  2. Copy the numeric Property ID (e.g., 123456789).

šŸ› ļø Available Tools

Tool NamePurpose
get_ga4_dataExecute GA4 queries with dimensions, metrics, date ranges, and optional filters.
search_schemaKeyword search across 200+ GA4 dimension and metric API names.
get_property_schemaInspect all available dimensions and metrics for your specific property.
list_metric_categoriesBrowse metric categories (User, Session, Revenue, Event).
list_dimension_categoriesBrowse dimension categories (Geography, Traffic Source, Device).
get_troubleshooting_guideSelf-healing guide for IAM permissions, setup, and filter syntax.

šŸ”’ Telemetry & Privacy

GA4 MCP collects anonymous usage telemetry to improve the server — no personal data, no GA4 report data, ever. Opt out anytime with DISABLE_TELEMETRY=1 or DO_NOT_TRACK=1.


šŸ“„ License & Author

Developed by Surendran B under the Apache License 2.0.
Website: https://ga4mcp.com

Latest Version

Version
1.0.0
Category
Other Tools and Integrations
Namespace
io.github.surendranb (imported)
Published
Jul 26, 2026
Updated
Jul 28, 2026