Google Tag Manager MCP Server
Enables interaction with Google Tag Manager containers, tags, triggers, and variables through natural language, using OAuth authentication.
README
Google Tag Manager (GTM) MCP Server
Google Tag Manager MCP server with OAuth authentication. Connects Claude.ai and other MCP clients directly to your GTM containers and tags via Google login — no server-side OAuth credentials required.
Built with Python FastMCP using RemoteAuthProvider, following the same zero-credential architecture as the GA4 and Google Search Console MCP servers.
How it works
The server uses FastMCP's RemoteAuthProvider which advertises Google as the authorization server. When you click Connect in Claude.ai, Claude handles the Google OAuth flow itself and passes the bearer token to the server. The server validates the token via Google's tokeninfo endpoint — no Google client secrets or keys needed on the server side.
Tools
list_accounts— Lists all GTM accounts you have access tolist_containers— Lists all containers within a specific GTM accountlist_workspaces— Lists active workspaces in a containerlist_tags— Displays all configured tags in a workspacelist_triggers— Displays all triggers (pageviews, clicks, custom events) in a workspacelist_variables— Lists all user-defined and built-in variables
Deployment on Coolify
1. Connect Repository in Coolify
Point Coolify at this public repository (https://github.com/sidiio/mcp-gtm).
Set Build Pack to Dockerfile.
2. Set Environment Variables
In your application environment settings, add:
| Variable | Value |
|---|---|
PORT |
8080 |
MCP_BASE_URL |
https://mcpgtm.tophathome.ca |
No Google client secrets or OAuth keys required in Coolify.
3. Connect in Claude.ai
- Open Claude.ai → Settings → Connectors (Integrations)
- Click Add custom integration
- URL:
https://mcpgtm.tophathome.ca - Click Connect → Google login pop-up appears → sign in with your account → done!
Local Development
pip install -e .
MCP_BASE_URL=http://localhost:8080 python -m gtm_mcp
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.
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.
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.
E2B
Using MCP to run code via e2b.
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.