Skip to main content
Glama
MCP Memory Server

MCP Memory Server

by PlumyCat

๐Ÿง  MCP Memory Server

TypeScript Node.js Azure Cosmos DB OpenAI

Advanced Memory System for Claude Desktop - Transform Claude into an AI assistant with photographic memory using MCP (Model Context Protocol).

โœจ What it does

Imagine Claude with persistent memory that:

  • ๐Ÿง  Remembers everything from your conversations

  • ๐Ÿ” Automatically retrieves context when you reference past topics

  • ๐Ÿค– Understands references like "that project", "this company", "he/she"

  • ๐Ÿ“ˆ Builds knowledge over time across all your sessions

  • ๐Ÿ› ๏ธ Auto-captures results from web searches and other tools

Related MCP server: Claude Memory MCP

๐Ÿš€ Quick Start

Prerequisites

  • Node.js 18+

  • Azure Cosmos DB account

  • OpenAI API key

  • Claude Desktop

Installation

git clone https://github.com/PlumyCat/mcp-memory-server.git
cd mcp-memory-server
npm install
npm run build

Configuration

  1. Environment setup:

cp .env.example .env
# Edit .env with your API keys
  1. Claude Desktop configuration:

{
  "mcpServers": {
    "memory": {
      "command": "node",
      "args": ["/path/to/mcp-memory-server/dist/index.js"],
      "cwd": "/path/to/mcp-memory-server"
    }
  }
}
  1. Test the magic:

You: "I'm working on a TypeScript project using CosmosDB"
Claude: [Responds normally + automatic background storage]

# Later...
You: "What was that project we discussed?"
Claude: "You mentioned working on a TypeScript project using CosmosDB..."

๐ŸŽฏ Key Features

๐Ÿง  Intelligent Memory Storage

  • Automatic entity extraction (people, companies, projects, tools)

  • Semantic storage with OpenAI embeddings

  • Conversation context preservation

  • Smart deduplication

๐Ÿ” Advanced Search & Retrieval

  • Semantic similarity search

  • Entity relationship mapping

  • Timeline-based retrieval

  • Context-aware responses

๐Ÿค– Entity Resolution

  • Automatic pronoun resolution ("he" โ†’ "John Smith")

  • Reference understanding ("that company" โ†’ "Microsoft")

  • Cross-conversation entity linking

  • Confidence scoring

๐Ÿ“Š Analytics & Insights

  • Conversation pattern analysis

  • Entity interaction timelines

  • Knowledge growth tracking

  • Usage statistics

๐Ÿ› ๏ธ Available Tools

The server provides 6 MCP tools for Claude:

Tool

Description

Example Usage

memory_store

Store information with auto entity extraction

Automatically triggered during conversations

memory_search

Semantic search through stored memories

"Find all discussions about React"

context_inject

Get relevant context for current query

"What did we discuss about this project?"

entity_resolve

Resolve references to actual entities

"Who is 'he' referring to?"

conversation_analyze

Analyze conversation patterns

"Show my discussion statistics"

memory_timeline

Get timeline of entity interactions

"Timeline of Microsoft mentions"

๐Ÿ“ Project Structure

mcp-memory-server/
โ”œโ”€โ”€ src/
โ”‚   โ”œโ”€โ”€ config/          # Azure Cosmos DB configuration
โ”‚   โ”œโ”€โ”€ memory/          # Core memory system (RAG, storage, graph)
โ”‚   โ”œโ”€โ”€ types/           # TypeScript type definitions
โ”‚   โ”œโ”€โ”€ utils/           # Entity extraction, context injection
โ”‚   โ””โ”€โ”€ server.ts        # Main MCP server implementation
โ”œโ”€โ”€ scripts/             # Maintenance and health check scripts
โ”œโ”€โ”€ tests/               # Unit and integration tests
โ”œโ”€โ”€ docs/                # Technical documentation
โ””โ”€โ”€ dist/                # Compiled JavaScript (generated)

๐Ÿ—๏ธ Architecture

Core Components

  • RAG System: Vector similarity search with OpenAI embeddings

  • Entity Extractor: NLP-based entity recognition with custom patterns

  • Memory Storage: Optimized CosmosDB integration with smart indexing

  • Context Injector: Intelligent context retrieval for conversations

  • Graph Engine: Entity relationship mapping and traversal

Data Flow

graph TD
    A[User Message] --> B[Entity Extraction]
    B --> C[Embedding Generation]
    C --> D[CosmosDB Storage]
    D --> E[Semantic Search]
    E --> F[Context Injection]
    F --> G[Enhanced Claude Response]

๐Ÿ”ง Configuration

Environment Variables

# Azure Cosmos DB
COSMOS_ENDPOINT=https://your-account.documents.azure.com:443/
COSMOS_KEY=your-primary-key
COSMOS_DATABASE_NAME=memory-db
COSMOS_CONTAINER_CONVERSATIONS=conversations
COSMOS_CONTAINER_ENTITIES=entities

# OpenAI
OPENAI_API_KEY=your-openai-api-key

# Optional
NODE_ENV=production
LOG_LEVEL=info
MEMORY_RETENTION_DAYS=30

Advanced Configuration

See Configuration Guide for detailed setup options.

๐Ÿงช Testing

# Run all tests
npm test

# Health check
npm run health-check

# Test memory functionality
npm run test-memory

๐Ÿ“Š Performance

  • Storage: Optimized CosmosDB indexing for sub-100ms queries

  • Search: Vector similarity with 95%+ accuracy

  • Memory: Efficient entity deduplication and compression

  • Scalability: Handles 1000+ entities with consistent performance

๐Ÿ›ฃ๏ธ Roadmap

โœ… Completed

  • Core memory storage and retrieval

  • Entity extraction and resolution

  • Semantic search with embeddings

  • CosmosDB integration

  • MCP server implementation

๐Ÿ”„ In Progress

  • Intelligent entity deduplication

  • Auto-capture of all MCP tool results

  • Enhanced entity classification patterns

  • Contradiction detection system

๐Ÿ”ฎ Planned

  • Multi-user memory isolation

  • Graph traversal with Gremlin queries

  • Advanced analytics dashboard

  • Memory compression and archiving

See Roadmap for detailed feature planning.

๐Ÿค Contributing

We welcome contributions! Please see our Contributing Guidelines for details.

Development Setup

git clone https://github.com/PlumyCat/mcp-memory-server.git
cd mcp-memory-server
npm install
npm run dev

๐Ÿ“š Documentation

๐Ÿ†˜ Support

๐Ÿ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.

๐Ÿ™ Acknowledgments

โญ Star History

Star History Chart


Made with โค๏ธ for the Claude Desktop community

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelogโ€ฆ

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      An MCP server that provides persistent memory capabilities for Claude, offering tiered memory architecture with semantic search, memory consolidation, and integration with the Claude desktop application.
      69
      MIT
    • F
      license
      A
      quality
      D
      maintenance
      A lightweight MCP server that provides Claude Desktop with persistent memory across conversations by storing, summarizing, and retrieving conversation history.
      3
      -
    • A
      license
      B
      quality
      C
      maintenance
      A persistent memory MCP server for Claude Code that automatically saves conversations and retrieves relevant history across sessions to provide context.
      17
      29 PyPI
      10
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      A persistent memory MCP server for Claude Code that enables long-term recall across sessions via hybrid search, code intelligence, and tools for reading/writing memory.
      5
      MIT