Memory MCP Server

Give your AI agent a persistent memory that survives across conversations. The Memory MCP server stores entities, relationships, and observations in a local knowledge graph that Claude can read and update. Features: - Store named entities (people, projects, concepts) with properties - Create relationships between entities - Add observations and notes to existing entities - Query the knowledge graph with natural language - Persistent storage — memory survives session restarts - Delete outdated or incorrect memories - Local storage — your data never leaves your machine Real-world use cases: - "Remember that our production database is on AWS us-east-1" - "Note that Alice is the lead on the payments project" - "Store my API keys and configurations" - Remember user preferences across sessions in AI applications This is one of the most-requested MCP capabilities and the official implementation is the most trusted option in the ecosystem.