MCP Memory Server

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

Imagine Claude withpersistent memorythat:

- 🧠Remembers everythingfrom your conversations
- 🔍Automatically retrieves contextwhen you reference past topics
- 🤖Understands referenceslike "that project", "this company", "he/she"
- 📈Builds knowledgeover time across all your sessions
- 🛠️Auto-capturesresults from web searches and other tools

- Node.js 18+
- Azure Cosmos DB account
- OpenAI API key
- Claude Desktop

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

cp .env.example .env # Edit .env with your API keys

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

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..."

- Automatic entity extraction (people, companies, projects, tools)
- Semantic storage with OpenAI embeddings
- Conversation context preservation
- Smart deduplication

- Semantic similarity search
- Entity relationship mapping
- Timeline-based retrieval
- Context-aware responses

- Automatic pronoun resolution ("he" → "John Smith")
- Reference understanding ("that company" → "Microsoft")
- Cross-conversation entity linking
- Confidence scoring

- Conversation pattern analysis
- Entity interaction timelines
- Knowledge growth tracking
- Usage statistics

The server provides 6 MCP tools for Claude:

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

- 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

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]

# 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

SeeConfiguration Guidefor detailed setup options.

# Run all tests npm test # Health check npm run health-check # Test memory functionality npm run test-memory

SeeRoadmapfor detailed feature planning.

We welcome contributions! Please see ourContributing Guidelinesfor details.

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

- Usage Guide- Comprehensive usage examples
- API Reference- Detailed API documentation
- Architecture- Technical architecture details
- Troubleshooting- Common issues and solutions

- 📖 Check theUsage Guidefor examples
- 🐛 Report issues onGitHub Issues
- 💬 Discuss onGitHub Discussions

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

- Model Context Protocol (MCP)for the foundational protocol
- Claude Desktopfor the AI assistant platform
- Azure Cosmos DBfor scalable data storage
- OpenAIfor embedding generation
- Compromise.jsfor natural language processing

Access Apache Gravitino, a high-performance, federated metadata lake for data and AI.