Google Analytics MCP for Coolify
Provides a secure FastMCP gateway to Google Analytics Admin and Data APIs, deployable on Coolify with OAuth protection and encrypted storage.
README
Google Analytics MCP for Coolify
This package places a secure FastMCP HTTP/OAuth gateway in front of Google's
official experimental analytics-mcp package. It is intended to be deployed as
a separate Coolify application and does not modify an existing Google Ads
MCP deployment.
What it provides
- Streamable HTTP MCP endpoint at
/mcp - Google OAuth protection for the remote MCP endpoint
- Encrypted persistent storage for MCP OAuth registrations and tokens
- Google Analytics Admin API and Data API tools from the official
analytics-mcppackage - Support for either authorized-user ADC JSON or a service-account JSON key
Required Coolify configuration
Create a persistent storage mount at /data and expose port 8080.
Set these environment variables in the new Analytics application:
| Variable | Purpose |
|---|---|
GOOGLE_PROJECT_ID |
Existing Google Cloud project ID |
GOOGLE_ANALYTICS_MCP_BASE_URL |
Final HTTPS origin, without /mcp |
GOOGLE_ANALYTICS_MCP_OAUTH_CLIENT_ID |
Google OAuth web client ID |
GOOGLE_ANALYTICS_MCP_OAUTH_CLIENT_SECRET |
Google OAuth web client secret |
GOOGLE_ANALYTICS_MCP_JWT_SIGNING_KEY |
Long random secret used to sign MCP tokens |
GOOGLE_ANALYTICS_MCP_STORAGE_ENCRYPTION_KEY |
Fernet key used to encrypt stored OAuth data |
GOOGLE_ANALYTICS_CREDENTIALS_JSON |
Analytics-authorized ADC JSON, entered as one secret value |
PORT is optional and defaults to 8080.
Google Cloud configuration
Enable both APIs in the same Google Cloud project:
- Google Analytics Admin API
- Google Analytics Data API
The OAuth client must be a Web application. Add this authorized redirect URI after the final domain is assigned:
https://YOUR-ANALYTICS-MCP-DOMAIN/auth/callback
The MCP URL added to ChatGPT is:
https://YOUR-ANALYTICS-MCP-DOMAIN/mcp
Important credential separation
Do not alter the existing Ads application or replace its credentials. The
GOOGLE_ANALYTICS_CREDENTIALS_JSON value belongs only to this separate
Analytics application and must include the
https://www.googleapis.com/auth/analytics.readonly scope.
When the Google OAuth consent screen is in Testing, Google may expire authorized-user refresh tokens after seven days. That is a Google OAuth testing limitation, not a Coolify failure.
Versions
analytics-mcp==0.7.0fastmcp==3.4.7- Python 3.11
The version pins make deployments repeatable. Review upstream releases before updating them.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.