Built-in MCP Configuration

Cherry Studio Comes with several common MCPs preinstalled, and can be used in Settings → MCP Servers without manual installation. Below is the current built-in list,New versions may adjust, please refer to what is actually shown in the app.

Want to install other MCPs yourself? See Configure and Use MCP.

General Tools

@cherry/fetch

An MCP server for fetching webpage content from URLs. The go-to choice when you want AI to "take a look at a webpage".

@cherry/browser

Controls a hidden Electron window through the Chrome DevTools Protocol, supporting opening URLs, running single-line JS, and resetting sessions. Suitable for scenarios where you need AI to operate a real browser and read dynamic webpages.

@cherry/filesystem

A Node.js MCP server that implements filesystem operations, allowing AI to read, create, and modify local files.You must configure the allowed directories, otherwise it cannot start:

WORKSPACE_ROOT=/Users/yourname/your-project-dir

If you don't configure the environment variable, you need to specify the path manually in the conversation.

@cherry/python

Executes Python code in a Pyodide sandbox, supporting most standard libraries and scientific computing packages. It's a great fit for letting AI "run some Python itself" to do data analysis, plotting, and format conversion.

@cherry/brave_search

Integrates Brave Search API search tool, providing both web and local search capabilities. You need to first apply for an API Key from Brave and configure the environment variable:

BRAVE_API_KEY=your_brave_api_key

Memory

@cherry/memory

A basic implementation of persistent memory based on a local knowledge graph, allowing the model to remember user-related information across different conversations. Requires configuring MEMORY_FILE_PATH environment variable:

MEMORY_FILE_PATH=/path/to/memory.json

Note: this is memory in MCP form.Cherry Studio's global memory is a higher-level feature; the two can be used together, but usually only one is needed.

@cherry/nowledge_mem

Integrate Nowledge Mem app, storing conversations, tools, notes, agents, and files in a local private memory system. You need to install Nowledge Mem locally first.

Thinking / Framework

@cherry/sequentialthinking

Provides a "structured thought process" tool that lets AI reason step by step when solving complex problems, with the ability to review and reflect during the reasoning process. Suitable for complex logical tasks.

@cherry/mcp-auto-install

Lets AI automatically search for and install other MCPs during the conversation (beta). See Automatically Install MCPs.

Domestic Service Integrations

@cherry/dify_knowledge

Access knowledge bases through the Dify platform. See Configure the Dify knowledge base.

@cherry/flomo

Connect flomo notes and let AI help you quickly record ideas. flomo account authorization is required.

@cherry/didi_mcp

Integrates Didi: map search, fare estimation, order management, driver tracking, and more.Only supports mainland China, requires configuring DIDI_API_KEY environment variable.

Summary

Use Cases	Recommended Built-in MCPs
Want AI to read webpages	@cherry/fetch or @cherry/browser
Want AI to search the web (structured results)	@cherry/brave_search
Want AI to handle local files	@cherry/filesystem
Want AI to run Python code	@cherry/python
Want AI to connect to a Dify knowledge base	@cherry/dify_knowledge
Want AI to have persistent memory	Prefer the higher-level one global memory, use the lower-level one only if you need advanced control @cherry/memory
Let AI help you install other MCPs	@cherry/mcp-auto-install

The activation method is the same: in Settings → MCP Servers find the corresponding item, fill in the environment variables as prompted, and click Enable.

---

💡 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.