> For the complete documentation index, see [llms.txt](https://docs.cherryai.com.cn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherryai.com.cn/docs/en-us/advanced-basic/mcp/builtin.md). # 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](/docs/en-us/advanced-basic/mcp/config.md). ### 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](https://brave.com/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**](/docs/en-us/advanced-basic/memory.md) is a higher-level feature; the two can be used together, but usually only one is needed. #### `@cherry/nowledge_mem` Integrate [Nowledge Mem](https://mem.nowledge.co/) 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](/docs/en-us/advanced-basic/mcp/auto-install.md). ### Domestic Service Integrations #### `@cherry/dify_knowledge` Access knowledge bases through the Dify platform. See [Configure the Dify knowledge base](/docs/en-us/advanced-basic/mcp/dify.md). #### `@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](/docs/en-us/advanced-basic/memory.md), 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](/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, and the optional `goal` query parameter: ``` GET https://docs.cherryai.com.cn/docs/en-us/advanced-basic/mcp/builtin.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.