# Built-in MCP Configuration ### @cherry/mcp-auto-install Automatically install MCP services (beta) ### @cherry/memory A persistent memory foundation implementation based on a local knowledge graph. This enables the model to remember relevant user information across different conversations. ```typescript MEMORY_FILE_PATH=/path/to/your/file.json ``` ### @cherry/sequentialthinking An MCP server implementation that provides tools for dynamic and reflective problem-solving through a structured thinking process. ### @cherry/brave-search An MCP server implementation integrated with the Brave Search API, providing both web and local search capabilities. ```typescript BRAVE_API_KEY=YOUR_API_KEY ``` ### @cherry/fetch An MCP server for retrieving webpage content from URLs. ### @cherry/filesystem A Node.js server implementing the Model Context Protocol (MCP) for file system operations. Environment variables: ``` WORKSPACE_ROOT=directory path address (optional) ``` If no environment variables are configured, you need to enter the path address during the model conversation --- # 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/buildin.md?ask= ``` 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.