Memory MCP Server

A Swift implementation of the Model Context Protocol (MCP) server, providing knowledge graph management capabilities. It allows LLMs to create, read, update, and delete entities and relations in a persistent knowledge graph, helping AI assistants maintain memory across conversations. This project is based on the official TypeScript Memory MCP Server.

The server features knowledge graph storage, entity management, relation tracking, an observation system, and powerful search capabilities. Data persists between sessions in a simple JSON format.

Available tools include create_entities, create_relations, add_observations, delete_entities, delete_observations, delete_relations, read_graph, search_nodes, and open_nodes. Installation is available via a one-line curl command or by building from source using swift build.

The server supports command-line arguments (-h, -v) and environment variables like MEMORY_FILE_PATH for custom storage paths. Configuration examples are provided for Claude.app, Cursor, and Chatwise.

Use cases include long-term memory for AI assistants, knowledge management, relationship tracking, context persistence, and maintaining journals.