# Configure and Use MCP

<figure><img src="/files/9763c9c02390032687c633a4f4a44e2d40937bfb" alt=""><figcaption></figcaption></figure>

1. Open Cherry Studio settings.
2. Find `MCP Server` option.
3. Click `Add server`.
4. Fill in the relevant parameters for the MCP Server ([reference link](https://github.com/modelcontextprotocol/servers/tree/main/src/fetch)). The information you may need to fill in includes:
   * Name: Customize a name, such as `fetch-server`
   * Type: Select `STDIO`
   * Command: Enter `uvx`
   * Arguments: Enter `mcp-server-fetch`
   * (there may be other parameters as well, depending on the specific Server)
5. Click `Save`.

{% hint style="success" %}
After completing the above configuration, Cherry Studio will automatically download the required MCP Server - `fetch server`. Once the download is complete, we can start using it! Note: if the mcp-server-fetch configuration is unsuccessful, you can try restarting the computer.
{% endhint %}

### Enable MCP service in the chat box

<figure><img src="/files/886164585fbc9fad7bc12aef2d3e0edabef50e0c" alt=""><figcaption></figcaption></figure>

* In `MCP Server` The settings successfully added the MCP server

<figure><img src="/files/512b1ec39c2c1cb307135f5df51fd1699b86e36e" alt=""><figcaption></figcaption></figure>

### **Usage demonstration**

<figure><img src="/files/3de1fcc6a3294d773fa8f8aa5f666a7da7a706f6" alt=""><figcaption></figcaption></figure>

As can be seen from the image above, after combining MCP's `edit` feature, Cherry Studio is able to better understand the user's query intent and obtain relevant information from the web, providing more accurate and comprehensive answers.


---

# 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/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.