> 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/docs/en-us/advanced-basic/mcp/config.md).

# Configure and Use MCP

This page uses a very common example — **letting AI access page content from the web**(called `fetch`, provided by the official MCP) — to walk you through a complete MCP configuration. Installing other MCPs later follows basically the same process.

> Don’t know what MCP is? Read first [Overview of the MCP Usage Tutorial](/docs/en-us/advanced-basic/mcp.md).

## Add an MCP (using fetch as an example)

<figure><img src="/files/9763c9c02390032687c633a4f4a44e2d40937bfb" alt=""><figcaption><p>MCP server add interface</p></figcaption></figure>

1. Open `Settings → MCP Servers`
2. Click `+ Add Server`
3. Fill in the following information in the pop-up form:

| Field         | What to fill in    | Explanation                                                                          |
| ------------- | ------------------ | ------------------------------------------------------------------------------------ |
| **Name**      | `fetch-server`     | Choose a name that’s easy to recognize; it won’t affect functionality                |
| **Type**      | `STDIO`            | This is the common "local command-line" type                                         |
| **Command**   | `uvx`              | Cherry Studio’s built-in Python tool will automatically download the required script |
| **Arguments** | `mcp-server-fetch` | Tell uvx which MCP to install                                                        |

4. Click `Save`, Cherry Studio will automatically download `fetch` this MCP (internet required the first time)

{% hint style="success" %}
**No obvious feedback after saving?** Some MCPs take a long time to download the first time (they need to fetch code from GitHub). You can click the server item to check the status:

* 🟢 Green = Ready
* 🟡 Yellow = Downloading or starting
* 🔴 Red = Failed, click to view error logs

If it stays red for a long time, please refer to [Frequently asked questions](https://github.com/CherryHQ/cherry-studio-docs/blob/main/advanced-basic/mcp/chang-jian-wen-ti.md) or restart Cherry Studio and try again.
{% endhint %}

## Where do these fields come from?

Different MCPs require different "commands" and "arguments". Check the MCP’s own documentation page:

* **Official MCP**: go to [github.com/modelcontextprotocol/servers](https://github.com/modelcontextprotocol/servers/tree/main/src/fetch) find the corresponding repository; the README at the top will provide a configuration example
* **Third-party MCP**: the developer’s GitHub README will also provide

Can’t read it? Let Cherry Studio help you: see [Automatically Install MCPs](/docs/en-us/advanced-basic/mcp/auto-install.md), just tell AI "help me install a fetch MCP".

## Let AI use MCP

After adding it, it’s only "installed"; you still need to tell the AI in**the chat that it can use**:

1. in [chat interface](/docs/en-us/cherry-studio/preview/chat.md) find it below the input box in **MCP tools** icon
2. Open it and check the server you just added
3. Ask normally, for example:**Help me fetch `https://docs.cherry-ai.com` the title and outline of this page**
4. The AI will automatically call the fetch MCP to get the webpage, then answer you

<figure><img src="/files/886164585fbc9fad7bc12aef2d3e0edabef50e0c" alt=""><figcaption><p>MCP tool selection in the chat box</p></figcaption></figure>

<figure><img src="/files/512b1ec39c2c1cb307135f5df51fd1699b86e36e" alt=""><figcaption><p>Select the enabled MCP servers</p></figcaption></figure>

### Effect demo

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

Without MCP, AI can only answer based on the "information it saw during training"; after connecting fetch, AI can "look it up online right now," so the answers are much more accurate.

## For [Cherry Agent](/docs/en-us/cherry-studio/preview/agent.md) install MCP

If you’re using Cherry Agent, the MCP integration location is different:

1. Enter Agent editing interface → `Tools` tab
2. Under the "MCP" group, check the servers you want this Agent to use
3. The Agent will decide on its own when to call it

## Want to install another one?

* Want AI to operate your local files → install **filesystem** MCP
* Want AI to operate the browser → install **playwright** MCP
* Want AI to check Notion → install **notion** MCP

All of these are in [the official repository](https://github.com/modelcontextprotocol/servers) with ready-made configuration examples; just copy and paste them.

***

### 💡 Get help and submit feedback

If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to [Feedback and Suggestions](/docs/en-us/question-contact/suggestions.md) the official channels provided there.


---

# 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/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.