> For the complete documentation index, see [llms.txt](https://docs.maiagent.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.maiagent.ai/tech/mcp.md).

# MaiAgent Build｜MCP 與外部服務

- [MCP（Model Context Protocol）](https://docs.maiagent.ai/tech/mcp/mcp-model-context-protocol.md): MCP（Model Context Protocol）是什麼：AI 應用連接外部工具與資料來源的開放協定，運作原理、核心價值，以及在 MaiAgent 用 MCP 工具接 MCP Server。
- [MaiAgent MCP：讓外部 AI 工具操作平台](https://docs.maiagent.ai/tech/mcp/maiagent-mcp.md): 讓 Claude、Cursor 等支援 MCP 的 AI 工具透過 MaiAgent MCP 操作平台：服務端點與提供的工具、API Key 與 OAuth 兩種連法、驗證與疑難排解
- [自架 MCP Server 接入規格](https://docs.maiagent.ai/tech/mcp/self-hosted-mcp-server.md): 把自家系統做成 MCP Server 讓 MaiAgent 的 Agent 呼叫：支援的傳輸方式與 URL 要求、驗證（固定標頭、聯絡人憑證、OAuth 動態註冊）、允許的工具、逾時重試與錯誤如何回給模型，以及 MCP Apps 互動卡片。
- [Remote MCP 服務概述](https://docs.maiagent.ai/tech/mcp/remote-mcp.md): Remote MCP（遠端 MCP 服務）的概念，以及 MaiAgent 怎麼連線 Composio、Zapier 等託管服務與自架的 MCP 伺服器：傳輸方式、驗證、工具範圍、逾時與紀錄，和使用時的注意事項。
- [Composio 串接](https://docs.maiagent.ai/tech/mcp/composio.md): Composio 串接：從 Composio MCP 目錄取得 MCP Server URL、連接第三方帳號，並在 MaiAgent 建立 MCP 工具供 Agent 使用。
- [Zapier 串接](https://docs.maiagent.ai/tech/mcp/zapier.md): Zapier MCP 串接：在 Zapier MCP 控制台建立 MCP Server、選擇開放給 AI 的動作（Actions）、複製 endpoint，並在 MaiAgent 建立 MCP 工具。


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.maiagent.ai/tech/mcp.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.