Claude Memory MCP Server logo

Claude Memory MCP Server

by WhenMoon-afk

An MCP server implementation that provides persistent memory capabilities for Large Language Models, specifically designed to integrate with the Claude desktop application. It implements optimal memory techniques based on comprehensive research of current approaches in the field.

View on GitHub

Last updated: N/A

What is Claude Memory MCP Server?

This is an MCP (Model Context Protocol) server that provides persistent memory capabilities for Large Language Models, specifically designed to integrate with the Claude desktop application. It allows Claude to maintain memory across conversations and sessions.

How to use Claude Memory MCP Server?

To use this server, you need to install it following the provided installation steps, configure your Claude desktop application to connect to the server, and then start the server. The server provides tools to store, retrieve, list, update, and delete memories.

Key features of Claude Memory MCP Server

  • Tiered Memory Architecture: Short-term, long-term, and archival memory tiers

  • Multiple Memory Types: Support for conversations, knowledge, entities, and reflections

  • Semantic Search: Retrieve memories based on semantic similarity

  • Memory Consolidation: Automatic consolidation of short-term memories into long-term memory

  • Memory Management: Importance-based memory retention and forgetting

  • Claude Integration: Ready-to-use integration with Claude desktop application

  • MCP Protocol Support: Compatible with the Model Context Protocol

Use cases of Claude Memory MCP Server

  • Maintaining context across multiple conversations with Claude.

  • Storing and retrieving knowledge for Claude to use in its responses.

  • Remembering entities and their relationships for improved understanding.

  • Providing Claude with a long-term memory for more personalized interactions.

FAQ from Claude Memory MCP Server

What is MCP?

MCP stands for Model Context Protocol, a standardized way for LLMs to maintain persistent memory.

What is the memory file structure?

The memory system uses a JSON-based file structure with metadata, memory index, short-term memory, long-term memory, archived memory, memory schema, and config.

How do I integrate this with Claude?

You need to add the provided configuration to your Claude configuration file, specifying the command and arguments to run the MCP server.

What are the available tools?

The available tools are store_memory, retrieve_memory, list_memories, update_memory, delete_memory, and memory_stats.

What research is this based on?

This implementation is based on comprehensive research of current LLM persistent memory techniques, including OS-inspired memory management, biological-inspired episodic memory, vector embeddings, and self-reflection.