# MCP Environment Installation

**MCP (Model Context Protocol)** is an open-source protocol designed to provide context information to large language models (LLMs) in a standardized way. For more information about MCP, see [Knowledge Basics](/docs/en-us/question-contact/knowledge.md#shen-me-shi-mcpmodel-context-protocol)

## Using MCP in Cherry Studio

Below, using the `edit` feature as an example, we will demonstrate how to use MCP in Cherry Studio. Details can be found in the [documentation](https://github.com/modelcontextprotocol/servers/tree/main/src/fetch) .

### **Preparation: Install uv and bun**

{% hint style="warning" %}
Cherry Studio currently only uses the built-in [uv](https://github.com/astral-sh/uv) and [bun](https://github.com/oven-sh/bun),**and will not reuse**the uv and bun already installed on the system.
{% endhint %}

In `Settings - MCP Server` , click the `Install` button to automatically download and install it. Because it is downloaded directly from GitHub, the speed may be relatively slow, and there is a high chance of failure. Whether the installation is successful depends on whether there are files in the folder mentioned below.

<figure><img src="/files/4a9cce1342636e34cb3f039766db08a52b767a57" alt=""><figcaption></figcaption></figure>

**Executable installation directory:**

Windows: `C:\Users\username\.cherrystudio\bin`

macOS, Linux: `~/.cherrystudio/bin`

<figure><img src="/files/0c8dc653f6196fc6657aa7652a06afd0fbdc2c76" alt=""><figcaption><p>bin directory</p></figcaption></figure>

**If installation fails normally:**

You can create a soft link for the corresponding command in the system to this location; if there is no corresponding directory, you need to create it manually. You can also manually download the executable file and place it in this directory:

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


---

# 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/docs/en-us/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.