This MCP server demonstrates a structured approach for using an MCP server with Mem0 to manage coding preferences efficiently. It is designed to work with Cursor by exposing an SSE endpoint for MCP clients to connect, retrieve, and semantically search stored coding preferences. The server exposes three core tools: add_coding_preference to store complete code snippets with context (dependencies, language/framework versions, setup instructions, documentation, examples, and best practices); get_all_coding_preferences to retrieve all stored coding preferences for analysis; and search_coding_preferences to perform semantic searches for relevant code implementations, solutions, best practices, setup guides, and documentation. By default, the server runs on 0.0.0.0:8080 and can be configured with command-line arguments like `uv run main.py --host <host> --port <port>`. It runs as an SSE-based process that agents connect to, use, and disconnect from as needed, enabling cloud-native, decoupled usage. Access Mem0 via MEM0_API_KEY in a .env file to authenticate with Mem0.