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

# MCP 环境安装

首次使用 MCP 前，需要安装两个底层工具：**uv** 与 **bun**。绝大多数 MCP Server 依赖其中之一启动。

> 推荐先阅读 [MCP 使用教程总览](/advanced-basic/mcp.md)。

无需了解 uv / bun 的技术细节，Cherry Studio 会**自动完成下载与安装**，仅需在界面中点击对应按钮。

## 自动安装（推荐）

{% hint style="warning" %}
Cherry Studio 用的是 **自己内置的** [uv](https://github.com/astral-sh/uv) 和 [bun](https://github.com/oven-sh/bun)，不会复用你电脑里可能已经装过的版本。所以即使你系统里已经有 uv / bun，也仍然需要按下面步骤再装一次给 Cherry Studio 用。
{% endhint %}

在 `设置 - MCP 服务器` 中，点击 `安装` 按钮，即可自动下载并安装。因为是直接从 GitHub 上下载，速度可能会比较慢，且有较大可能失败。安装成功与否，以下文提到的文件夹内是否有文件为准。

<figure><img src="/files/cZ96C263LtuOBahYZ2au" alt=""><figcaption></figcaption></figure>

**可执行程序安装目录：**

{% tabs %}
{% tab title="Windows" %}
`C:\Users\用户名\.cherrystudio\bin`
{% endtab %}

{% tab title="macOS / Linux" %}
`~/.cherrystudio/bin`
{% endtab %}
{% endtabs %}

<figure><img src="/files/XY3uXaiDtYB89AhNoSsX" alt=""><figcaption><p>bin 目录</p></figcaption></figure>

**无法正常安装的情况下：**

可以将系统中的相对应命令使用软链接的方式链接到这里，如果没有对应目录，需要手动建立。也可以手动下载可执行文件放到这个目录下面：

Bun: <https://github.com/oven-sh/bun/releases>\
UV: <https://github.com/astral-sh/uv/releases>

***

### 💡 获取帮助与提交反馈

如果您在配置或使用过程中遇到任何疑问、Bug 或有功能改进建议，请参考 [反馈与建议](/question-contact/suggestions.md) 中提供的官方渠道。


---

# 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 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/install.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.