For the complete documentation index, see llms.txt. This page is also available as Markdown.

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.

Add an MCP (using fetch as an example)

MCP server add interface
  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

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

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 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, 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 inthe chat that it can use:

  1. in chat interface 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

MCP tool selection in the chat box
Select the enabled MCP servers

Effect demo

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 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 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 the official channels provided there.

Last updated

Was this helpful?