analytics-mcp

What it is and what it does

analytics-mcp is an MCP (Model Context Protocol) server that bridges Google Analytics APIs to large language models like Claude and Gemini. It wraps the Google Analytics Admin API and Google Analytics Data API, exposing them as tools that an LLM can call to query account summaries, property details, run standard and funnel reports, retrieve real-time data, and fetch custom dimensions and metrics.

The package is designed to run as a local server that integrates with Gemini CLI, Gemini Code Assist, or Claude Code. Once configured with Google Cloud credentials and added to your LLM client's MCP server list, it allows you to ask natural-language questions about your analytics data directly within your AI assistant—for example, asking for the most popular events in the last 180 days or details about signed-in users. It requires Python 3.10 or later and depends on google-auth, google-analytics-data, google-analytics-admin, mcp, google-adk, and httpx.

Use it for:

• Ask an LLM for a summary of your Google Analytics accounts and properties without leaving your IDE or chat interface.
• Query analytics reports and funnel data through natural language prompts in Gemini or Claude.
• Retrieve real-time analytics metrics and custom dimensions/metrics for a property via LLM conversation.
• Automate analytics exploration and reporting by having an LLM analyze your GA4 data and suggest insights.
• Integrate analytics queries into AI-assisted code development workflows within Gemini Code Assist.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Runs an MCP server that exposes Google Analytics Admin and Data APIs as tools for LLMs, enabling queries about accounts, properties, reports, and real-time analytics data.

Yes, if you use Gemini CLI, Gemini Code Assist, or Claude Code and want to query Google Analytics through natural language. The package is actively maintained, has no known vulnerabilities, uses a permissive license, and low install friction. However, it requires Google Cloud setup (enabling APIs, configuring credentials) and is not a standalone library—it only works as an MCP server within a compatible LLM client.

Install

analytics-mcp on PyPI

pip install analytics-mcp

uv add analytics-mcp

poetry add analytics-mcp

Installing analytics-mcp

Before you install

Low install friction with a pure-Python wheel. Actively maintained as of 2026-08-07 with recent releases. Requires Python 3.10 or later and depends on six Google-authored packages (google-analytics-data, google-analytics-admin, google-auth, mcp, google-adk, httpx), all standard infrastructure.

License in practice

Licensed under Apache-2.0 (permissive), allowing free use, modification, and distribution with minimal restrictions—suitable for both commercial and open-source projects.

Quickstart

pip install analytics-mcp

# Then configure credentials via Application Default Credentials (ADC)
# and add to ~/.gemini/settings.json or Claude MCP config:
# {
#   "mcpServers": {
#     "analytics-mcp": {
#       "command": "pipx",
#       "args": ["run", "analytics-mcp"],
#       "env": {
#         "GOOGLE_APPLICATION_CREDENTIALS": "PATH_TO_CREDENTIALS_JSON",
#         "GOOGLE_PROJECT_ID": "YOUR_PROJECT_ID"
#       }
#     }
#   }
# }

# Then use in Gemini CLI or Claude Code with prompts like:
# "what are the most popular events in my Google Analytics property in the last 180 days?"

Requires Google Cloud project with Google Analytics Admin API and Google Analytics Data API enabled, plus Application Default Credentials configured with analytics.readonly scope. Intended for use as an MCP server within Gemini CLI, Gemini Code Assist, or Claude Code—not a standalone library.

Verify before relying

• Whether the package works with Python versions beyond 3.13 (classifiers list 3.10–3.13 but requires_python only specifies >=3.10)
• Performance characteristics when running large or complex analytics queries through the MCP interface
• Whether all Google Analytics Admin and Data API features are exposed or only a subset

Package facts

Evidence: analytics_mcp-0.7.0-py3-none-any.whl

Keywords: google analytics, analytics, mcp, ga4

Tags

More Internet packages

Further reading