Google Tag Manager MCP

Google Tag Manager MCP

English | Русский

A1 Google Tag Manager MCP lets an AI app inspect and manage Google Tag Manager containers in plain language. See what fires on a page, work with tags, triggers and variables in a draft workspace, then deliberately compile and publish a version when you are ready.

It connects to the Google Tag Manager API v2 through your Google account. The difference from asking an AI to guess a GTM setup is that it works with the actual container, workspace and version you choose.

• 25 tools. 10 operations only read GTM data; 4 create drafts or change built-in variables; 5 can alter, delete, compile or publish live configuration.
• Connects from the conversation. Say "connect Google Tag Manager": the server walks you through the OAuth client, catches Google's redirect on 127.0.0.1 with PKCE and keeps the tokens itself — no config files, no restart.
• Draft first. Tags, triggers and variables are created in a workspace. Publishing is a separate, explicitly destructive operation.
• Quota-aware. GTM permits 0.25 requests per second per project; the server spaces requests by at least 4.2 seconds instead of overwhelming the API.
• Your Google access. The server uses your OAuth credentials and requests only the Tag Manager scopes needed for reading, editing, versioning and publishing.

Start with a read-only question:

Which tags in my containers fire on the page-view trigger?

Connect the server · Explore use cases · Open technical documentation

See it work in a minute

You: List my GTM containers and show which tags fire on page view.

Assistant: Lists the containers, their workspaces, relevant triggers and the tags attached to them. Nothing changes.

You: In the Default Workspace of GTM-ABC123, prepare a GA4 configuration tag for measurement ID G-XXXXXXX on all pages.

Assistant: Shows the workspace, proposed tag and trigger configuration, then asks for confirmation before creating the draft.

You: Confirm the draft.

Assistant: Creates the tag in the workspace. It does not publish the container; compiling and publishing a version remains a separate step.

Contents

• Quick start
• What you can ask it to do
• How GTM changes are connected
• What can change
• Getting access
• Configuration
• Data and telemetry
• Limits and background work
• Technical documentation
• Support

Quick start

You need Node.js 20+ and a Google account. Credentials are not required at install time — the server connects from the conversation.

1. Add the server to your AI app.
2. Say "connect Google Tag Manager": the assistant walks you through creating the OAuth client and approving access without editing config files.
3. Start with the read-only question above.

Codex

In the app:

1. Open Settings → MCP servers.
2. Select Add server.
3. Choose STDIO, then enter npx -y mcp-google-tagmanager@latest and the three environment variables below.

1. Select Save, then Restart.

From the command line:

codex mcp add google-tagmanager \
  -- npx -y mcp-google-tagmanager@latest

codex mcp list

Codex MCP documentation

Claude Code

claude mcp add \
  --transport stdio \
  --scope user \
  google-tagmanager \
  -- npx -y mcp-google-tagmanager@latest

claude mcp list

Claude Code MCP documentation

Claude Desktop

The current official path is Settings → Extensions. For a custom desktop extension, open Advanced settings → Extension Developer → Install Extension…, select a .mcpb file and follow the prompts.

This repository currently publishes an npm stdio package and does not contain a .mcpb bundle. For Claude Desktop builds that still support local configuration, use the following JSON stdio configuration as a fallback:

{
  "mcpServers": {
    "google-tagmanager": {
      "command": "npx",
      "args": ["-y", "mcp-google-tagmanager@latest"]
    }
  }
}

In those builds, save it to ~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows.

Claude Desktop MCP documentation

Cursor

Add a user-level server to ~/.cursor/mcp.json on macOS/Linux or %USERPROFILE%\.cursor\mcp.json on Windows:

{
  "mcpServers": {
    "google-tagmanager": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "mcp-google-tagmanager@latest"]
    }
  }
}

Cursor MCP documentation

VS Code

Run MCP: Open User Configuration from the Command Palette and add:

{
  "servers": {
    "google-tagmanager": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "mcp-google-tagmanager@latest"]
    }
  }
}

Check it with MCP: List Servers.

VS Code MCP documentation

What you can ask it to do

Understand the current setup

• List the GTM accounts and containers I can access.
• Which tags fire on page view in this workspace?
• Show the trigger and variable configuration for this tag.
• Which built-in variables are enabled?

Prepare tracking changes in a draft

• Create a workspace for the checkout tracking change.
• Prepare a GA4 tag and a trigger for a specific event.
• Enable the click variables needed for this trigger.
• Update this tag after showing me the complete replacement configuration.

Release a version deliberately

• Compile this workspace into a version named April release.
• Show the compiler errors, if any.
• Publish version 42 after I confirm the version and its changes.

How GTM changes are connected

GTM has a clear release path:

1. An account contains one or more containers.
2. A container has workspaces for draft changes.
3. Tags, triggers and variables belong to a workspace.
4. Compiling a workspace creates a container version and removes the source workspace. GTM provides a replacement workspace.
5. Publishing makes a selected container version live.

This server can inspect each step. It does not treat a draft as a release: version creation and publishing are separate operations.

What can change

The AI client decides how it asks for confirmation. The server marks read-only, write and destructive operations so the client can distinguish inspection from a real change.

Getting access

Google Tag Manager requires OAuth 2.0; an API key is not enough. There are two ways in, and the first one needs no configuration files.

Connect from the chat (recommended)

Say "connect Google Tag Manager" and the assistant runs the flow with you:

1. setup_instructions prints the checklist: create or select a Google Cloud project, enable Tag Manager API, configure the consent screen and create a Desktop app OAuth client.
2. Download that client's JSON ("Download JSON") and give the assistant its path — set_client stores it owner-only. The secret never goes through the conversation.
3. start_login returns a Google consent link. Open it on this machine and approve; the code comes back to a one-shot listener on 127.0.0.1 (PKCE), never through the chat.
4. finish_login exchanges the code and saves the tokens to ~/.config/mcp-google-tagmanager/credentials.json (mode 0600) and verifies them with a real Tag Manager API call — so an API that is still switched off is caught right there.

The tokens are re-read on every call, so the connection works immediately — no restart of the AI app. auth_status shows what is connected, logout revokes and deletes it.

Environment variables (CI, unattended installs)

1. Create or select a Google Cloud project and enable the Tag Manager API. A project without that API enabled receives no quota.
2. Configure the OAuth consent screen and create an OAuth client. A Desktop app client is suitable for local use.
3. Authorize your Google account and obtain a refresh token. The OAuth 2.0 Playground can do this if you enable Use your own OAuth credentials.
4. Request these scopes together:

    https://www.googleapis.com/auth/tagmanager.readonly
    https://www.googleapis.com/auth/tagmanager.edit.containers
    https://www.googleapis.com/auth/tagmanager.edit.containerversions
    https://www.googleapis.com/auth/tagmanager.publish

The scopes are separate: reading, editing, compiling versions and publishing each need their corresponding permission. Treat the client secret and refresh token as passwords.

Configuration

Every variable is optional — with none of them the server connects from the chat.

\* Provide either the OAuth trio or an access token. Access tokens expire in about an hour and are not refreshed automatically.

Data and telemetry

The server runs locally and sends GTM API requests and OAuth refresh requests to Google. Its anonymous telemetry contains a random installation ID, package version, AI client and Node.js/operating-system versions, and tool names. It does not send OAuth tokens, GTM data, tool arguments or prompts.

Disable telemetry for A1 MCP servers with:

ASKADS_TELEMETRY=0

Limits and background work

• GTM is rate-limited. The API allows 0.25 requests per second per project, so the server serializes calls at least 4.2 seconds apart. Broad audits can therefore take time.
• Temporary limits are retried carefully. 429 and Google quota 403 responses use exponential backoff and Retry-After. Reads retry after network and 5xx failures; writes are not replayed after an uncertain failure.
• There is no background monitoring. The server runs only when your AI app calls it. If the app supports scheduled tasks, it can periodically inspect a container or its live version.
• A workspace disappears when compiled. Before calling create_version, save anything you need from the workspace and inspect the returned replacement workspace path.

Technical documentation

• MCP capability catalog — task-oriented pages for every tool.
• All tools and inputs
• Development documentation
• Publishing documentation
• Google Tag Manager API v2 reference

Support

Found a bug or need a scenario? Create an issue or write in Telegram.

You made it to the end!