Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the Mintlify 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
Trigger Mintlify documentation updates, query analytics, and manage assistant queries via the Mintlify API. 5 tools, Bearer-token auth.
试试这样问
Mintlify 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 → Mintlify、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Mintlify + Gemini
Trigger Mintlify documentation updates, query analytics, and manage assistant queries via the Mintlify API. 5 tools, Bearer-token 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:
MINTLIFY_API_KEY
步骤 1 — 获取凭证
com/docs/api-reference).
Setup:
- Sign in to https://dashboard.mintlify.com → Settings → API Keys → Create API key.
- Copy the key (starts with
mint_). SetMINTLIFY_API_KEY.
Authentication: Authorization: Bearer ${MINTLIFY_API_KEY}.
Mintlify's API is scoped: most write operations (trigger update, manage content) are not exposed because Mintlify expects content to live in a git repo and update on push. The API focuses on:
- Triggering re-deploys
- Querying assistant (chat) interactions
- Pulling analytics / search data
Out of scope here: page/content CRUD (manage via the git repo), team management, OAuth user actions.
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—Mintlify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 |
|---|---|
mintlify_trigger_update | Trigger a re-deploy of the documentation site (forces Mintlify to pull from the connected git repo and re-build) |
mintlify_get_project_info | Get project metadata: name, repo, deployment status, custom domain |
mintlify_list_assistant_conversations | List user conversations with the Mintlify AI assistant on your docs site |
mintlify_list_search_queries | List user search queries on the docs site (analytics) |
mintlify_get_analytics | Retrieve site analytics aggregations (pageviews, unique visitors, top pages) for a date range |
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?
