No install? Use cloud.anythingmcp.com directly.
Sign in, install the Heap in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Send events, identify users and update properties in Heap (product analytics) from any AI agent. 5 tools, app_id-based auth.
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → Heap、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Heap + Gemini
Send events, identify users and update properties in Heap (product analytics) from any AI agent. 5 tools, app_id-based 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:
HEAP_APP_ID
步骤 1 — 获取凭证
heap.io/docs/server-side-apis).
Setup:
- Sign in to https://app.heap.io → top-right → Account → Projects → select project → Project ID (called
app_id). - Set
HEAP_APP_IDto the numeric app/project ID.
Authentication: NONE — Heap's server-side API uses the app_id in the request body to route events to your project. There's no secret on the ingestion endpoint (anyone with your app_id can fake events — same trust model as Google Analytics client-side JS).
…(continued in the in-app connector instructions)
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—Heap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 |
|---|---|
heap_track_event | Track a single behavioral event for a user |
heap_bulk_track | Bulk-track many events in one call (up to 1000 events, 1MB total) |
heap_add_user_properties | Set or update user-level properties (Heap merges with existing) |
heap_add_account_properties | Set or update properties on an account (B2B model — accounts group users) |
heap_add_user_to_account | Associate a user (identity) with an account (account_id) |
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
这份指南对您有帮助吗?