Skip to main content

GTM MCP Server

PyPI version Python Version License: MIT

A Model Context Protocol (MCP) server that enables Claude to interact with Google Tag Manager.

Table of Contents

Features

⬆ top

  • List GTM accounts and containers
  • Manage tags, triggers, and variables
  • Create and publish container versions
  • Full workspace management

🚀 Quick Start

⬆ top

Prerequisites

  • Python 3.10 or higher
  • Claude Desktop (or any MCP-compatible client like Cursor)
  • A Google account with access to Google Tag Manager

🔧 Setup Instructions

⬆ top

Configure Python

Install the package using pip or pipx:

pip install gtm-mcp

See PyPi


Enable Tag Manager API

  1. Go to Google Cloud Console
  2. Create a new project or select an existing one
  3. Go to "APIs & Services" → "Library"
  4. Search for "Tag Manager API"
  5. Click on it and click "Enable"

Configure Credentials

This server uses Application Default Credentials (ADC) for authentication. You need to set up credentials that have access to your Google Tag Manager accounts.

Step 1: Create a Service Account

  1. Go to Google Cloud Console
  2. Navigate to "APIs & Services" → "Credentials"
  3. Click "Create Credentials" → "Service Account"
  4. Fill in the service account details:
    • Service account name: gtm-mcp-service
    • Description: Service account for GTM MCP Server
  5. Click "Create and Continue"
  6. Skip optional steps and click "Done"

Step 2: Create and Download Service Account Key

  1. Click on the service account you just created
  2. Go to the "Keys" tab
  3. Click "Add Key" → "Create New Key"
  4. Select "JSON" format
  5. Click "Create"
  6. The JSON file will download automatically
  7. Save this file securely - you'll need its path later
  8. Copy the service account email (looks like: gtm-mcp-service@your-project.iam.gserviceaccount.com)

Step 3: Grant Service Account Access to GTM

  1. Go to Google Tag Manager
  2. Select your GTM account
  3. Click "Admin" in the top navigation
  4. Under "Account", click "User Management"
  5. Click the "+" button to add a user
  6. Enter the service account email from Step 2
  7. Select appropriate permissions:
    • Read: For read-only access
    • Edit: For creating/modifying tags, triggers, variables
    • Approve: For publishing container versions
    • Publish: For full publishing rights
  8. Click "Invite"

Configure Claude Desktop

Edit your Claude Desktop config file:

  • Linux: ~/.config/Claude/claude_desktop_config.json
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Add your configuration:

{
  "mcpServers": {
    "gtm-mcp": {
      "command": "gtm-mcp",
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/your/service-account-key.json",
        "GOOGLE_PROJECT_ID": "your-project-id"
      }
    }
  }
}

Important: Replace the values with your actual paths and project ID.

Example paths:

  • Linux/macOS: /home/username/gtm-service-account.json
  • Windows: C:\\Users\\YourName\\gtm-service-account.json

To find your Project ID:

  • Look in the Google Cloud Console top bar, next to your project name
  • Or find it in your service account JSON file under the "project_id" field

Try It Out

  1. Restart Claude Desktop completely (close and reopen)
  2. Ask Claude: "List my GTM accounts"
  3. Authentication will happen automatically using the service account credentials!

🛠️ Available Tools

⬆ top

Once configured, Claude will have access to these GTM tools:

Tool Description
gtm_list_accounts List all your GTM accounts
gtm_list_containers List containers in an account
gtm_list_tags List tags in a workspace
gtm_get_tag Get detailed configuration of a specific tag
gtm_create_tag Create a new tag
gtm_update_tag Update an existing tag
gtm_list_triggers List triggers in a workspace
gtm_create_trigger Create a new trigger
gtm_list_variables List variables in a workspace
gtm_get_variable Get detailed configuration of a specific variable
gtm_create_variable Create a new variable (constant, data layer, cookie, URL, etc.)
gtm_publish_container Create and publish a new container version
gtm_list_versions List all versions of a container
gtm_get_version Get detailed information about a specific version
gtm_get_live_version Get the currently published (live) version
gtm_get_latest_version Get the latest version (may not be published)
gtm_delete_version Delete (archive) a container version
gtm_undelete_version Restore a deleted version
gtm_update_version Update version metadata (name, description, notes)
gtm_set_latest_version Mark a version as the latest

❓ Troubleshooting

⬆ top

"Missing required environment variable" Error

Problem: The MCP server can't find the required environment variables.

Solution:

  1. Ensure both GOOGLE_APPLICATION_CREDENTIALS and GOOGLE_PROJECT_ID are set in your Claude Desktop config
  2. Verify the path to your service account JSON file is correct and absolute
  3. On Windows, use double backslashes: C:\\Users\\...
  4. Restart Claude Desktop after editing the config

"Failed to load Application Default Credentials" Error

Problem: The credentials file cannot be loaded or is invalid.

Solution:

  1. Verify the service account JSON file exists at the specified path
  2. Check that the JSON file is valid and not corrupted
  3. Ensure the file has proper read permissions
  4. Try downloading a new key from Google Cloud Console

"Service account has no access" Error

Problem: The service account doesn't have permission to access your GTM account.

Solution:

  1. Go to GTM → Admin → User Management
  2. Verify the service account email is listed with appropriate permissions
  3. Grant at least "Read" permission (or higher based on your needs)

Can't Access GTM Accounts

Possible causes:

  • Service account doesn't have GTM permissions
  • Tag Manager API isn't enabled in your Google Cloud project
  • Wrong service account email was added to GTM

Solution:

  1. Verify Tag Manager API is enabled in Google Cloud Console
  2. Check that the service account email is added to your GTM account
  3. Ensure proper permissions are granted in GTM User Management

Package Not Found After Install

Problem: gtm-mcp command not found after installation.

Solution:

# Ensure pip install location is in PATH
pip install --user gtm-mcp

# Or use pipx for isolated installation
pipx install gtm-mcp

🔒 Security Notes

⬆ top

  • Keep your JSON key file secure - it provides full access to whatever permissions you've granted
  • Never commit the JSON file to version control - add it to .gitignore
  • Use restrictive file permissions - chmod 600 service-account.json on Unix/Linux
  • Store the file in a secure location with limited access
  • You can create new keys and delete old ones in Google Cloud Console
  • Regularly rotate service account keys for better security
  • This server only accesses GTM - no other Google services
  • Credentials are only used for Google Tag Manager API authentication
  • No credentials are sent to any third-party services

💻 Development

Running Tests

pip install -e ".[dev]"
pytest

📝 License

⬆ top

See LICENSE file for details


🤝 Contributing

⬆ top

Contributions are welcome! Please:

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Submit a pull request

For bugs and feature requests, please open an issue.


🆘 Getting Help

⬆ top

If you encounter issues:

  1. Check the Troubleshooting section above
  2. Review Claude Desktop logs for error messages
  3. Verify your Google Cloud project has Tag Manager API enabled
  4. Ensure environment variables are set correctly in the config
  5. Open an issue on GitHub with:
    • Your operating system
    • Python version (python --version)
    • Error messages from Claude Desktop logs
    • Steps to reproduce the issue

Metadata

Release files for unboundai-gtm-mcp 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for unboundai-gtm-mcp 0.1.1
File Size Uploaded Provenance Actions
unboundai_gtm_mcp-0.1.1.tar.gz 43.7 kB Without provenance Details for unboundai_gtm_mcp-0.1.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for unboundai-gtm-mcp 0.1.1
File Interpreter ABI Platform Actions
unboundai_gtm_mcp-0.1.1-py3-none-any.whl Python 3 none any Details for unboundai_gtm_mcp-0.1.1-py3-none-any.whl

Total release size: 91.0 kB

Release files / unboundai_gtm_mcp-0.1.1.tar.gz

Download URL unboundai_gtm_mcp-0.1.1.tar.gz
Size 43.7 kB
Tags Source
SHA-256 checksum
How to use checksums
5fadae7e39aa7f20aeeb1edf2448d2be34ac303dca717c0b70e0bc10b547407b
BLAKE2b-256 checksum
How to use checksums
ffdac53fc9084b6fb500cd7778ef57e6c8bb8860c7919db88c266501b2260567
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/2.2.1 CPython/3.11.5 Windows/10

Release files / unboundai_gtm_mcp-0.1.1-py3-none-any.whl

Download URL unboundai_gtm_mcp-0.1.1-py3-none-any.whl
Size 47.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
80ab9f545595ab9de124a0f49a3086cf3fcc944d0512e6f5303e4fb193838dc5
BLAKE2b-256 checksum
How to use checksums
01140569d43c503a2d1ddc88dc9631484f1594b84bf5e38db38ce66b158d8d0f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/2.2.1 CPython/3.11.5 Windows/10

Security for unboundai-gtm-mcp 0.1.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page