This is the experimental local MCP server published by the Google Analytics repository. It wraps Admin API and Data API reporting capabilities into MCP tools so clients such as Gemini CLI, Gemini Code Assist, and Claude Code can answer natural-language questions about accounts, properties, core reports, funnel reports, and realtime reports. It suits analysts who already have a Google Cloud project and can configure read-only ADC credentials, and it is not intended for users who cannot set up credentials or who need write operations. The main risks are its experimental status and the handling of the local credentials file.
Strongest · Setup experience 14/20 Weakest · Reliability 9/20
Static review · not runListed 2026-09-18
Read the FMRS scoring method →Runtime：Python 3.10+ · Prebuilt binary
GOOGLE_APPLICATION_CREDENTIALS
Path to the Application Default Credentials JSON file generated via gcloud auth application-default login; credentials must include the analytics.readonly scope.
GOOGLE_PROJECT_ID
Your Google Cloud project ID with the Google Analytics Admin API and Data API enabled; find it in the Google Cloud console.
{
"mcpServers": {
"analytics-mcp": {
"command": "pipx",
"args": ["run", "analytics-mcp"],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "PATH_TO_CREDENTIALS_JSON",
"GOOGLE_PROJECT_ID": "YOUR_PROJECT_ID"
}
}
}
}
Shown for Claude Code. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"analytics-mcp": {
"command": "pipx",
"args": [
"run",
"analytics-mcp"
],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "PATH_TO_CREDENTIALS_JSON",
"GOOGLE_PROJECT_ID": "YOUR_PROJECT_ID"
}
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add analytics-mcp -e GOOGLE_APPLICATION_CREDENTIALS=PATH_TO_CREDENTIALS_JSON -e GOOGLE_PROJECT_ID=YOUR_PROJECT_ID -- pipx run analytics-mcp
Run it in a terminal; replace any <…> placeholders with your own values first.
Launch Gemini CLI or Gemini Code Assist and type /mcp; confirm analytics-mcp and its tools (e.g. get_account_summaries, run_report) appear. Alternatively ask "what are the most popular events in my Google Analytics property in the last 180 days?" — a data-backed answer proves the connection.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
This is the source for a local MCP server from the Google Analytics repository that exposes Google Analytics account, property, and reporting capabilities to LLMs through the Google Analytics Admin API and Data API. It runs locally and requires Python (pipx), Google Analytics credentials via Application Default Credentials with the read-only scope, and registration in a client such as Gemini CLI, Gemini Code Assist, or Claude Code. The repository labels the server as experimental.
Manage your Hevy workout data from AI assistants via MCP.
Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
One binary. One grammar. Evidence from the biomedical sources you already trust.
Encrypted, fully offline long-term memory for AI agents
Source revision a7b483f2b02c Data synced 2026-11-02 Read the FMRS scoring method