google-tag-manager-mcp-server and gtm-mcp-server

These are competing server-side Google Tag Manager (GTM) MCP implementations, with both offering a server to manage GTM functionality, albeit with B specifically highlighting LLM integration.

gtm-mcp-server
40
Emerging
Maintenance 13/25
Adoption 10/25
Maturity 15/25
Community 21/25
Maintenance 10/25
Adoption 7/25
Maturity 11/25
Community 12/25
Stars: 115
Forks: 43
Downloads:
Commits (30d): 0
Language: TypeScript
License: Apache-2.0
Stars: 30
Forks: 4
Downloads:
Commits (30d): 0
Language: Go
License: BSD-3-Clause
No Package No Dependents
No Package No Dependents

About google-tag-manager-mcp-server

stape-io/google-tag-manager-mcp-server

MCP server for Google Tag Manager

Provides programmatic access to Google Tag Manager API operations through Claude and other MCP clients via OAuth-authenticated remote connections. Built on the MCP protocol with stdio transport, it enables AI assistants to manage GTM containers, tags, and variables directly. Integrates with Claude Desktop and compatible MCP clients through standard configuration, handling credential management automatically via Google's OAuth flow.

About gtm-mcp-server

paolobietolini/gtm-mcp-server

An MCP server for Google Tag Manager. Connect it to your LLM, authenticate once, and start managing GTM through natural language.

Implements a full GTM management API via Model Context Protocol with support for tags, triggers, variables, and server-side containers—powered by OAuth 2.1 PKCE authentication that works across Claude, ChatGPT, Gemini, and Cursor clients using streamable HTTP transport. Built in Go and designed for both single-user and agency workflows, it includes AI-driven auditing, tracking plan generation, and bulk operations without storing user credentials. The server operates as a client-agnostic MCP endpoint compatible with Dynamic Client Registration, enabling AI assistants to create GA4 setups, manage consent logic, and publish changes with built-in safety confirmations.

Scores updated daily from GitHub, PyPI, and npm data. How scores work