MCP Memory Service

An MCP server providing semantic memory and persistent storage capabilities for Claude Desktop using ChromaDB and sentence transformers. This service enables long-term memory storage with semantic search capabilities, making it ideal for maintaining context across conversations and instances.

Features

• Semantic search using sentence transformers
• Natural language time-based recall (e.g., "last week", "yesterday morning")
• Tag-based memory retrieval system
• Persistent storage using ChromaDB
• Automatic database backups
• Memory optimization tools
• Exact match retrieval
• Debug mode for similarity analysis
• Database health monitoring
• Duplicate detection and cleanup
• Customizable embedding model
• Cross-platform compatibility (Apple Silicon, Intel, Windows, Linux)
• Hardware-aware optimizations for different environments
• Graceful fallbacks for limited hardware resources

Quick Start

For the fastest way to get started:

Docker and Smithery Integration

Docker Usage

The service can be run in a Docker container for better isolation and deployment:

To configure Docker's file sharing on macOS:

1. Open Docker Desktop
2. Go to Settings (Preferences)
3. Navigate to Resources -> File Sharing
4. Add any additional paths you need to share
5. Click "Apply & Restart"

Smithery Integration

The service is configured for Smithery integration through smithery.yaml. This configuration enables stdio-based communication with MCP clients like Claude Desktop.

To use with Smithery:

1. Ensure your claude_desktop_config.json points to the correct paths:

2. The smithery.yaml configuration handles stdio communication and environment setup automatically.

Testing with Claude Desktop

To verify your Docker-based memory service is working correctly with Claude Desktop:

1. Build the Docker image with docker build -t mcp-memory-service .
2. Create the necessary directories for persistent storage:
   mkdir -p $HOME/mcp-memory/chroma_db $HOME/mcp-memory/backups
3. Update your Claude Desktop configuration file:
   • On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • On Windows: %APPDATA%\Claude\claude_desktop_config.json
   • On Linux: ~/.config/Claude/claude_desktop_config.json
4. Restart Claude Desktop
5. When Claude starts up, you should see the memory service initialize with a message:
   MCP Memory Service initialization completed
6. Test the memory feature:
   • Ask Claude to remember something: "Please remember that my favorite color is blue"
   • Later in the conversation or in a new conversation, ask: "What is my favorite color?"
   • Claude should retrieve the information from the memory service

If you experience any issues:

• Check the Claude Desktop console for error messages
• Verify Docker has the necessary permissions to access the mounted directories
• Ensure the Docker container is running with the correct parameters
• Try running the container manually to see any error output

For detailed installation instructions, platform-specific guides, and troubleshooting, see our documentation:

• Installation Guide - Comprehensive installation instructions for all platforms
• Troubleshooting Guide - Solutions for common issues
• Technical Documentation - Detailed technical procedures and specifications
• Scripts Documentation - Overview of available scripts and their usage

Configuration

Standard Configuration (Recommended)

Add the following to your claude_desktop_config.json file to use UV (recommended for best performance):

Windows-Specific Configuration (Recommended)

For Windows users, we recommend using the wrapper script to ensure PyTorch is properly installed. See our Windows Setup Guide for detailed instructions.

The wrapper script will:

1. Check if PyTorch is installed and properly configured
2. Install PyTorch with the correct index URL if needed
3. Run the memory server with the appropriate configuration

Hardware Compatibility

Memory Operations

The memory service provides the following operations through the MCP server:

Core Memory Operations

1. store_memory - Store new information with optional tags
2. retrieve_memory - Perform semantic search for relevant memories
3. recall_memory - Retrieve memories using natural language time expressions
4. search_by_tag - Find memories using specific tags
5. exact_match_retrieve - Find memories with exact content match
6. debug_retrieve - Retrieve memories with similarity scores

For detailed information about tag storage and management, see our Tag Storage Documentation.

Database Management

7. create_backup - Create database backup
8. get_stats - Get memory statistics
9. optimize_db - Optimize database performance
10. check_database_health - Get database health metrics
11. check_embedding_model - Verify model status

Memory Management

12. delete_memory - Delete specific memory by hash
13. delete_by_tag - Delete all memories with specific tag
14. cleanup_duplicates - Remove duplicate entries

Configuration Options

Configure through environment variables:

Getting Help

If you encounter any issues:

1. Check our Troubleshooting Guide
2. Review the Installation Guide
3. For Windows-specific issues, see our Windows Setup Guide
4. Contact the developer via Telegram: t.me/doobeedoo

Project Structure

Development Guidelines

• Python 3.10+ with type hints
• Use dataclasses for models
• Triple-quoted docstrings for modules and functions
• Async/await pattern for all I/O operations
• Follow PEP 8 style guidelines
• Include tests for new features

License

MIT License - See LICENSE file for details

Acknowledgments

• ChromaDB team for the vector database
• Sentence Transformers project for embedding models
• MCP project for the protocol specification

Contact

t.me/doobidoo

Cloudflare Worker Implementation

A serverless implementation of the MCP Memory Service is now available using Cloudflare Workers. This implementation:

• Uses Cloudflare D1 for storage (serverless SQLite)
• Uses Workers AI for embeddings generation
• Communicates via Server-Sent Events (SSE) for MCP protocol
• Requires no local installation or dependencies
• Scales automatically with usage

Benefits of the Cloudflare Implementation

• Zero local installation: No Python, dependencies, or local storage needed
• Cross-platform compatibility: Works on any device that can connect to the internet
• Automatic scaling: Handles multiple users without configuration
• Global distribution: Low latency access from anywhere
• No maintenance: Updates and maintenance handled automatically

Available Tools in the Cloudflare Implementation

The Cloudflare Worker implementation supports all the same tools as the Python implementation:

Configuring Claude to Use the Cloudflare Memory Service

Add the following to your Claude configuration to use the Cloudflare-based memory service:

Replace your-worker-subdomain with your actual Cloudflare Worker subdomain.

Deploying Your Own Cloudflare Memory Service

1. Clone the repository and navigate to the Cloudflare Worker directory:
   git clone https://github.com/doobidoo/mcp-memory-service.git cd mcp-memory-service/cloudflare_worker
2. Install Wrangler (Cloudflare's CLI tool):
   npm install -g wrangler
3. Login to your Cloudflare account:
   wrangler login
4. Create a D1 database:
   wrangler d1 create mcp_memory_service
5. Update the wrangler.toml file with your database ID from the previous step.
6. Initialize the database schema:
   wrangler d1 execute mcp_memory_service --local --file=./schema.sql
   Where schema.sql contains:
   CREATE TABLE IF NOT EXISTS memories ( id TEXT PRIMARY KEY, content TEXT NOT NULL, embedding TEXT NOT NULL, tags TEXT, memory_type TEXT, metadata TEXT, created_at INTEGER ); CREATE INDEX IF NOT EXISTS idx_created_at ON memories(created_at);
7. Deploy the worker:
   wrangler deploy
8. Update your Claude configuration to use your new worker URL.

Testing Your Cloudflare Memory Service

After deployment, you can test your memory service using curl:

1. List available tools:
   curl https://your-worker-subdomain.workers.dev/list_tools
2. Store a memory:
   curl -X POST https://your-worker-subdomain.workers.dev/mcp \ -H "Content-Type: application/json" \ -d '{"method":"store_memory","arguments":{"content":"This is a test memory","metadata":{"tags":["test"]}}}'
3. Retrieve memories:
   curl -X POST https://your-worker-subdomain.workers.dev/mcp \ -H "Content-Type: application/json" \ -d '{"method":"retrieve_memory","arguments":{"query":"test memory","n_results":5}}'

Limitations

• Free tier limits on Cloudflare Workers and D1 may apply
• Workers AI embedding models may differ slightly from the local sentence-transformers models
• No direct access to the underlying database for manual operations
• Cloudflare Workers have a maximum execution time of 30 seconds on free plans