Skip to main content
Glama
unboundai-gtm-mcp-server

unboundai-gtm-mcp-server

by tijevlam

MCP Server for Google Tag Manager

This is an MCP server that provides an interface to the Google Tag Manager API using Google Application Default Credentials (ADC).

Setup instructions

Setup involves the following steps:

  1. Install Node.js (v20 or later recommended)

  2. Enable Google Tag Manager API in your Google Cloud project

  3. Configure Google Application Default Credentials (ADC)

  4. Configure your MCP client (Claude Desktop, Gemini CLI, etc.)

Enable Google Tag Manager API

Follow the instructions to enable the Google Tag Manager API in your Google Cloud project:

Configure Google Application Default Credentials

Configure your Application Default Credentials (ADC). Make sure the credentials are for a user with access to your Google Tag Manager accounts.

Credentials must include the Google Tag Manager edit scope:

https://www.googleapis.com/auth/tagmanager.edit.containers

Check out Manage OAuth Clients for how to create an OAuth client.

Here are some sample gcloud commands you might find useful:

  • Set up ADC using user credentials and an OAuth desktop or web client after downloading the client JSON to YOUR_CLIENT_JSON_FILE.

    gcloud auth application-default login \
      --scopes https://www.googleapis.com/auth/tagmanager.edit.containers,https://www.googleapis.com/auth/cloud-platform \
      --client-id-file=YOUR_CLIENT_JSON_FILE
  • Set up ADC using service account impersonation.

    gcloud auth application-default login \
      --impersonate-service-account=SERVICE_ACCOUNT_EMAIL \
      --scopes=https://www.googleapis.com/auth/tagmanager.edit.containers,https://www.googleapis.com/auth/cloud-platform

When the gcloud auth application-default command completes, copy the PATH_TO_CREDENTIALS_JSON file location printed to the console in the following message. You'll need this for the next step!

Credentials saved to file: [PATH_TO_CREDENTIALS_JSON]

Configure Claude Desktop

  1. Open Claude Desktop and navigate to Settings -> Developer -> Edit Config. This opens the configuration file that controls which MCP servers Claude can access.

  2. Add the following configuration. Replace PATH_TO_CREDENTIALS_JSON with the path you copied in the previous step:

{
  "mcpServers": {
    "unboundai-gtm-mcp-server": {
      "command": "npx",
      "args": ["-y","@unboundai/gtm-mcp-server"],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "PATH_TO_CREDENTIALS_JSON"
      }
    }
  }
}
  1. Restart Claude Desktop. The tools will become available for you to use.

Related MCP server: GTM MCP Server

Troubleshooting

MCP Server Name Length Limit

Some MCP clients (like Cursor AI) have a 60-character limit for the combined MCP server name + tool name length. If you use a longer server name in your configuration (e.g., unboundai-gtm-mcp-server-your-additional-long-name), some tools may be filtered out.

To avoid this issue:

  • Use shorter server names in your MCP configuration (e.g., unboundai-gtm-mcp-server)

Debugging Server Issues

If the MCP server crashes or encounters issues, you can enable comprehensive debug logging to diagnose the problem:

  1. Enable Debug Mode: Set the DEBUG environment variable to true or 1:

    {
      "mcpServers": {
        "unboundai-gtm-mcp-server": {
          "command": "npx",
          "args": ["-y", "@unboundai/gtm-mcp-server"],
          "env": {
            "GOOGLE_APPLICATION_CREDENTIALS": "PATH_TO_CREDENTIALS_JSON",
            "DEBUG": "true"
          }
        }
      }
    }
  2. Control Log Level: Alternatively, set the LOG_LEVEL environment variable to control logging verbosity:

    • DEBUG: Shows all debug messages (most verbose)

    • INFO: Shows informational messages and above (default)

    • WARN: Shows only warnings and errors

    • ERROR: Shows only error messages

    Example:

    {
      "mcpServers": {
        "unboundai-gtm-mcp-server": {
          "command": "npx",
          "args": ["-y", "@unboundai/gtm-mcp-server"],
          "env": {
            "GOOGLE_APPLICATION_CREDENTIALS": "PATH_TO_CREDENTIALS_JSON",
            "LOG_LEVEL": "DEBUG"
          }
        }
      }
    }
  3. Check MCP Client Logs: The debug output is written to stderr and will appear in your MCP client's logs. In Claude Desktop:

    • macOS: ~/Library/Logs/Claude/mcp*.log

    • Windows: %APPDATA%\Claude\logs\mcp*.log

Debug logging provides detailed information about:

  • Server initialization and startup

  • Environment configuration

  • Authentication with Google APIs

  • Tool registration

  • API calls and responses

  • Error details with stack traces

Note: Debug logging may produce verbose output. It's recommended to enable it only when troubleshooting issues.

Available Tools

18 tools
gtm_accountA

Performs all account-related operations: get, list, update. Use the 'action' parameter to select the operation.

Inputs: action (required), accountId (required), config.

gtm_built_in_variableC

Performs all built-in variable operations: create, list, remove, revert. The 'list' action returns up to itemsPerPage items per page.

Inputs: action (required), accountId (required), containerId (required), workspaceId (required), +5 more.

gtm_clientB

Performs all client operations: create, get, list, update, remove, revert. The 'list' action returns up to itemsPerPage items per page.

Inputs: action (required), accountId (required), containerId (required), workspaceId (required), +5 more.

gtm_containerB

Performs all container-related operations: create, get, update, remove, list, combine, lookup, moveTagId, snippet. The 'list' action returns up to itemsPerPage items per page.

Inputs: action (required), accountId (required), page, containerId, +6 more.

gtm_destinationC

Performs all destination operations: get, list, link, unlink. The 'list' action returns up to 50 items per page.

Inputs: action (required), accountId (required), containerId (required), page, +3 more.

gtm_environmentC

Performs all environment operations: create, get, list, update, remove, reauthorize. The 'list' action returns up to 50 items per page.

Inputs: action (required), accountId (required), containerId (required), page, +4 more.

gtm_folderB

Performs all folder operations: create, get, list, update, remove, revert, entities, moveEntitiesToFolder. The 'list' action returns up to 50 items per page.

Inputs: action (required), accountId (required), containerId (required), workspaceId (required), +8 more.

gtm_gtag_configA

Performs all Google tag config operations: create, get, list, update, remove. The 'list' action returns up to itemsPerPage items per page.

Inputs: action (required), accountId (required), containerId (required), workspaceId (required), +5 more.

gtm_tagC

Performs all GTM tag operations: create, get, list, update, remove, revert. The 'list' action returns up to 20 items per page.

Inputs: action (required), accountId (required), containerId (required), workspaceId (required), +5 more.

gtm_templateB

Performs all GTM custom template operations: create, get, list, update, remove, revert. The 'list' action returns up to itemsPerPage items per page.

Inputs: action (required), accountId (required), containerId (required), workspaceId (required), +5 more.

gtm_transformationC

Performs all GTM transformation operations: create, get, list, update, remove, revert. The 'list' action returns up to itemsPerPage items per page.

Inputs: action (required), accountId (required), containerId (required), workspaceId (required), +5 more.

gtm_triggerA

Performs all GTM trigger operations: create, get, list, update, remove, revert. The 'list' action returns up to 20 items per page.

Inputs: action (required), accountId (required), containerId (required), workspaceId (required), +5 more.

gtm_user_permissionB

Performs all user permission operations: create, get, list, update, remove. The 'list' action returns up to 50 items per page.

Inputs: action (required), accountId (required), page, itemsPerPage, +2 more.

gtm_variableB

Performs all GTM variable operations: create, get, list, update, remove, revert. The 'list' action returns up to 20 items per page.

Inputs: action (required), accountId (required), containerId (required), workspaceId (required), +5 more.

gtm_versionA

Performs all container version operations: get, live, publish, remove, setLatest, undelete, update. For 'get' and 'live' actions, use 'resourceType' to paginate specific resource arrays (up to 20 items per page) to avoid response truncation.

Inputs: action (required), accountId (required), containerId (required), page, +6 more.

gtm_version_headerB

Performs all container version header operations: list, latest. The 'list' action returns up to 50 items per page.

Inputs: action (required), accountId (required), containerId (required), page, +2 more.

gtm_workspaceB

Performs various workspace operations including create, get, list, update, remove, createVersion, getStatus, sync, quickPreview, and resolveConflict actions. The 'list' action returns up to 50 items per page.

Inputs: action (required), accountId (required), containerId (required), page, +6 more.

gtm_zoneB

Performs various zone operations including create, get, list, update, remove, and revert actions. The 'list' action returns up to 20 items per page.

Inputs: action (required), accountId (required), containerId (required), workspaceId (required), +5 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 18 tools

    Disambiguation5/5

    Each tool is named after a distinct GTM resource, and there is no overlap in the resource types they operate on. Examples include gtm_container, gtm_tag, and gtm_account, which clearly separate concerns.

    Naming Consistency5/5

    All tools follow a consistent pattern of 'gtm_' followed by the resource name (e.g., gtm_workspace, gtm_trigger). No mixing of naming conventions or verb styles.

    Tool Count5/5

    With 18 tools covering the main GTM entities (containers, tags, triggers, workspaces, etc.), the count is well-scoped for a comprehensive management server. Each tool earns its place.

    Completeness5/5

    The toolset covers all major GTM resource types, including containers, accounts, workspaces, tags, triggers, variables, environments, folders, and more. Only niche or rarely used entities are absent, making the surface complete for typical GTM management.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      MCP server for Google Tag Manager API v2, enabling programmatic management of accounts, containers, workspaces, tags, triggers, variables, and version workflows.
      40 npm
      15
      MIT
    • F
      license
      Not graded
      quality
      B
      maintenance
      A remote MCP server for Google Tag Manager that enables AI assistants to manage GTM accounts, containers, tags, triggers, variables, and more via OAuth or service account authentication.
      1
      -
    • A
      license
      A
      quality
      F
      maintenance
      An MCP server for the Google Tag Manager API v2 that enables AI assistants to query GTM accounts, containers, tags, triggers, variables, and unpublished changes.
      24
      1
      Apache 2.0