gtm-mcp
Enables full Google Tag Manager management via the GTM API v2, including tags, triggers, variables, and version publishing, with workspace-based change tracking.
README
gtm-mcp
MCP server for full Google Tag Manager management via the GTM API v2: tags, triggers, variables and versions.
Tools (22)
Hierarchy: Account → Container → Workspace → (Tags / Triggers / Variables)
| Tool | What it does |
|---|---|
get_accounts |
List accessible GTM accounts — entry point |
get_containers |
Containers in an account |
get_workspaces |
Workspaces in a container (usually "Default Workspace") |
get_workspace_status |
Pending changes vs. the published version |
get_tags / get_tag |
List or detail tags |
create_tag / update_tag / delete_tag / revert_tag |
Tag CRUD |
get_triggers / get_trigger |
List or detail triggers |
create_trigger / update_trigger / delete_trigger |
Trigger CRUD |
get_variables |
List variables |
create_variable / update_variable / delete_variable |
Variable CRUD |
get_versions |
History of published versions |
create_version |
Snapshot the current workspace (restore point) |
publish_version |
Publish a version to production |
Typical flow
1. get_accounts() → account_id
2. get_containers(account_id) → container_id
3. get_workspaces(account_id, container_id) → workspace_id
4. get_workspace_status(...) → review pending changes
5. [create/edit tags, triggers, variables]
6. create_version(account_id, container_id, workspace_id, name="v1")
7. publish_version(account_id, container_id, version_id)
Setup
- Create a Google Cloud project (or reuse one) and enable the Tag Manager API.
- Create an OAuth 2.0 Client ID of type "Desktop app" and download it as
client_secret.json. - If the app is in "Testing" mode, add your Google account as a test user.
- Install dependencies:
python3 -m venv .venv source .venv/bin/activate pip install -r requirements.txt - Run the OAuth flow once:
This opens a browser — log in and grant access. Credentials are saved toCLIENT_SECRET_PATH=~/.config/gtm-mcp/client_secret.json python3 setup_auth.py~/.config/gtm-mcp/credentials.json.
⚠️ Only enable this MCP when you're actually working on GTM — leaving it always-on in a client that doesn't cache the OAuth session can trigger the auth flow on every startup.
MCP client configuration
{
"mcpServers": {
"gtm": {
"command": "/path/to/.venv/bin/python3",
"args": ["/path/to/gtm-mcp/server.py"]
}
}
}
| Env var | Default | Purpose |
|---|---|---|
GOOGLE_GTM_CREDENTIALS |
~/.config/gtm-mcp/credentials.json |
Path to the credentials file generated by setup_auth.py |
Notes
- All changes (create/edit/delete) stay in the workspace until published
with
create_version+publish_version. update_tag/update_trigger/update_variabledo a GET before the PUT to preserve unspecified fields — you won't lose parameters by omission.- Common
tag_typevalues:googtag(GA4/Google Tag),html(custom HTML),gclidw(Ads conversion),ua(legacy Universal Analytics). - Common
trigger_typevalues:pageview,customEvent,linkClick,formSubmission,domReady. - Common
variable_typevalues:v(Data Layer),k(Cookie),u(URL),jsm(Custom JS). parametersis a list of{type, key, value}wheretypeis one oftemplate,boolean,integer,listormap.
License
MIT — see LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。