How to configure the MCP Server for Google Tag Manager

Model Context Protocol (MCP) Server provides interoperability and coordination between AI models and tools. It is especially helpful in systems where many AI agents are working together. For the end user, it means smooth command performance and convenient data retrieval without the need to write API requests themselves.

We, at Stape, have developed the MCP Server for Google Tag Manager so you can manage and perform required actions more easily within a tool. Setting it up comes down to just a few steps:

1. 1.
   Make sure Node.js v18 or higher is installed and download the AI app you chose (in our case it's the Claude desktop app).
2. 2.
   Open the app and go to Settings → Developer → Edit Config.
3. 3.
   Replace the config file content with the GTM MCP Server configuration snippet (Stape users can also add their specific API key script here).
4. 4.
   Save the config, restart Claude Desktop, and complete the OAuth authentication flow to grant the required permissions to your Google Account.
5. 5.
   Verify that the GTM tools are now available in Claude.

The full detailed guide with step-by-step instructions and configuration snippets is available further in this article.

🤔 Are you going to configure the GTM MCP server in Claude? Check our guide to Claude MCP to understand how the protocol works and see best practices for using MCP in Claude.

After configuring the MCP Server (in our case, for Google Tag Manager), you can type any request in your AI app (e.g., the Claude app). Your request is sent to the MCP Server via the MCP Protocol (standard protocol for AI communication). Once the request is received, the MCP Server handles it (performs actions/commands or returns some data you requested).

The request can refer to most commands connected with GTM functionality and its entities. It includes, but is not limited to:

• Creating, getting, updating, removing accounts, workspaces, containers, and environments.
• Creating, getting, reverting, updating, removing clients, tags, triggers, variables, folders, and templates.
• Listing, getting, and managing the latest GTM container and header versions.
• Managing users’ permissions.

To configure the MCP Server for GTM, you will need:

• Node.js (v18 or higher)
• AI app or agent. In our example, we’ll use the Claude app. See installation instructions for other services.
  

We’ll cover two ways to configure an MCP server:

1. 1.
   Using HTTP connection - generally a better option, as long as your MCP client supports it. It prevents a lot of bugs and is way easier to install.
2. 2.
   Using mcp-remote - more complicated and error-prone, but can be the only option for some MCP clients (or if you specifically wish to use it for your setup).

1. Open Claude Desktop and go to File → Settings → Connectors → click Add to create a custom connector.

2. Set the name to gtm-mcp-server and the URL to https://gtm-mcp.stape.ai/mcp, then click Continue.

3. For Authentication, select Sign in now → for OAuth client, select Register automatically → click Add. 

4. On the new screen, click Connect (or click the new connector in the Connectors list). 

5. A new browser page will open - click Continue connecting and go through the Google OAuth flow.

6. After the access is granted, the tool will be available for your use.

7. Now you can type your request via chat. To verify that it’s working, just type any query related to your GTM account, like “List all my GTM entities” or “What's the total number of events across all sites this month?”

1. Open Claude Desktop and navigate to Settings → Developer → Edit Config → open desktop JSON file called claude_desktop_config. 

This opens Claude's JSON configuration file, which is where Claude stores information about the MCP servers it can connect to. Every MCP server that you want Claude to use must be defined in this configuration file.

2. Replace the file content with the following configuration.

3. Save the changes by pressing Cmd + S.

3. Restart Claude. When Claude starts again, it will attempt to connect to the added MCP server.

4. Authenticate with OAuth.

A browser window will open showing your OAuth login page. Complete the authentication flow to grant Claude access to your MCP server.

5. After you grant access, the tools will become available for you to use.

5. Now you can type your request via chat.

In Settings → Developer, you will see the status Running next to google-tag-manager-mcp-server. If you encounter any problems with configuration, refer to the troubleshooting section below.

MCP remote stores all the credential information inside ~/.mcp-auth (or wherever your MCP_REMOTE_CONFIG_DIR points to). If you're having persistent issues, try running:

It will clear any locally stored state and tokens. Then restart your MCP client.

Setting up an MCP Server for Google Tag Manager significantly simplifies interacting with GTM resources. For a user, there is no need for manual API requests. With our implementation, you can integrate this functionality into your workflow. Whether you're managing tags, containers, or user permissions, the MCP Server acts as a reliable bridge between your AI tools and GTM. We hope this guide helps you get started quickly!