# 配置和使用 MCP

<figure><img src="https://3562065924-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F0Ut5BptC3t8CtSU1UWpM%2Fuploads%2Fgit-blob-7745f89a2719a67fe564cf1fd4347e4fb8a5852f%2Fimage%20(8)%20(1).png?alt=media" alt=""><figcaption></figcaption></figure>

1. 打开 Cherry Studio 设置。
2. 找到 `MCP 服务器` 选项。
3. 点击 `添加服务器`。
4. 将 MCP Server 的相关参数填入（[参考链接](https://github.com/modelcontextprotocol/servers/tree/main/src/fetch)）。可能需要填写的内容包括：
   * 名称：自定义一个名称，例如 `fetch-server`
   * 类型：选择 `STDIO`
   * 命令：填写 `uvx`
   * 参数：填写 `mcp-server-fetch`
   * （可能还有其他参数，视具体 Server 而定）
5. 点击 `保存`。

{% hint style="success" %}
完成上述配置后，Cherry Studio 会自动下载所需的 MCP Server - `fetch server`。下载完成后，我们就可以开始使用了！注意：当 mcp-server-fetch 配置不成功的时候，可以尝试重启一下电脑。
{% endhint %}

### 在聊天框中启用 MCP 服务

<figure><img src="https://3562065924-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F0Ut5BptC3t8CtSU1UWpM%2Fuploads%2Fgit-blob-96a58008a3a9264d145c1af54cd47dc13e88a90d%2FMCP-%E8%BE%93%E5%85%A5%E6%A1%86%E6%8C%89%E9%92%AE%E7%A4%BA%E4%BE%8B.png?alt=media" alt=""><figcaption></figcaption></figure>

* 在 `MCP 服务器` 设置成功添加了 MCP 服务器

<figure><img src="https://3562065924-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F0Ut5BptC3t8CtSU1UWpM%2Fuploads%2Fgit-blob-1cf4883a7c3cb8d6c087771f24bc50c5e3727c63%2FMCP%E6%9C%8D%E5%8A%A1%E5%99%A8%E7%A4%BA%E4%BE%8B.png?alt=media" alt=""><figcaption></figcaption></figure>

### **使用效果展示**

<figure><img src="https://3562065924-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F0Ut5BptC3t8CtSU1UWpM%2Fuploads%2Fgit-blob-a2f11ef1cc115ec1fd7318b0592fdcd9a54e309c%2Fimage%20(1)%20(1)%20(1)%20(1)%20(1)%20(1).png?alt=media" alt=""><figcaption></figcaption></figure>

从上图可以看出，结合了 MCP 的 `fetch` 功能后，Cherry Studio 能够更好地理解用户的查询意图，并从网络上获取相关信息，给出更准确、更全面的回答。


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.cherry-ai.com/advanced-basic/mcp/config.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.