Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the Google Analytics 4 in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.
Summary
Query Google Analytics 4 (account/property metadata, custom dimensions/metrics, core reports, realtime reports, funnel reports) from any AI agent. 8 tools, OAuth2 user auth.
试试这样问
Google Analytics 4 的示例提示
点击任意提示即可复制，然后粘贴到 Claude、ChatGPT、Cursor、Gemini、Copilot 或 OpenClaw 中，在该连接器上运行。
Claude 是 AI，可能会出错。请核对回答。
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → Google Analytics 4、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Google Analytics 4 + Gemini
Query Google Analytics 4 (account/property metadata, custom dimensions/metrics, core reports, realtime reports, funnel reports) from any AI agent. 8 tools, OAuth2 user auth.
前提条件
完整的设置说明已内置在连接器中 (在 store 中选择连接器时可见)。所需环境变量:
GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, GOOGLE_REFRESH_TOKEN
步骤 1 — 获取凭证
This connector wraps the Google Analytics Data API v1beta (analyticsdata.googleapis.com) and Admin API v1beta (analyticsadmin.googleapis.com) — the same two APIs the official googleanalytics/google-analytics-mcp server uses.
Setup — OAuth2 user flow (one-time per account):
- Go to https://console.cloud.google.com → pick or create a project.
- APIs & Services → Library → enable both:
- Google Analytics Admin API (https://console.cloud.google.com/apis/library/analyticsadmin.googleapis.com)
- Google Analytics Data API (https://console.cloud.google.com/apis/library/analyticsdata.googleapis.com)
- …
步骤 2 — 安装 adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
步骤 3 — 在 Gemini 中添加连接器
Gemini CLI 从 ~/.gemini/settings.json (Windows: %APPDATA%\gemini\settings.json) 读取 MCP 服务器。添加:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- 从 AnythingMCP 获取你的 MCP API key。
- 保存文件并重启
gemini。 - 在 Gemini CLI 中运行
/mcp—Google Analytics 4应显示为可用。 - Vertex AI Studio: 将
https://cloud.anythingmcp.com/mcp传入请求的tools数组,使用相同的 Bearer 头。
可用工具
| Tool | What it does |
|---|---|
ga4_get_account_summaries | List the user's GA4 accounts and their properties (account ID, account name, property IDs, display names) |
ga4_get_property_details | Get detailed info about one GA4 property: display name, create time, time zone, currency, parent account, industry category, service level, |
ga4_list_google_ads_links | List Google Ads accounts linked to a GA4 property (useful to confirm conversion attribution wiring) |
ga4_list_custom_dimensions | List custom dimensions defined on a property — use these parameterName values in dimensions of ga4_run_report |
ga4_list_custom_metrics | List custom metrics defined on a property — use these parameterName values in metrics of ga4_run_report |
ga4_run_report | Run a core analytics report |
ga4_run_realtime_report | Run a realtime report (last 30 minutes of activity) |
ga4_run_funnel_report | Run a funnel report — measures conversion at each step of a user journey (e |
FAQ
Gemini 1.5 Pro 或 2.x 支持 MCP 吗? 支持 — Gemini CLI ≥ 0.4 与 Vertex AI tools API 均接受带 Bearer 头的 MCP httpUrl 连接器。
下一步
这份指南对你有帮助吗?
