Skip to main content
Glama
alphaplapplap

MCP Memory Service

MCP Memory Service

License: Apache 2.0 GitHub stars Production Ready

Works with Claude Works with Cursor MCP Protocol Multi-Client

Universal MCP memory service with intelligent memory triggers, OAuth 2.1 team collaboration, and semantic memory search for AI assistants. Features Natural Memory Triggers v7.1.0 with 85%+ trigger accuracy, Claude Code HTTP transport, zero-configuration authentication, and enterprise security. Works with Claude Desktop, VS Code, Cursor, Continue, and 13+ AI applications with SQLite-vec for fast local search and Cloudflare for global distribution.

๐Ÿš€ Quick Start (2 minutes)

๐Ÿง  v7.1.0: Natural Memory Triggers for Claude Code

๐Ÿค– Intelligent Memory Awareness (Zero Configuration):

# 1. Install MCP Memory Service
git clone https://github.com/doobidoo/mcp-memory-service.git
cd mcp-memory-service && python install.py

# 2. Install Natural Memory Triggers
cd claude-hooks && ./install-natural-triggers.sh

# 3. Test intelligent triggers
node memory-mode-controller.js status
# โœ… Done! Claude Code now automatically detects when you need memory context

๐Ÿ“– Complete Guide: Natural Memory Triggers v7.1.0


๐Ÿ†• v7.0.0: OAuth 2.1 & Claude Code HTTP Transport

๐Ÿ”— Claude Code Team Collaboration (Zero Configuration):

# 1. Start OAuth-enabled server
export MCP_OAUTH_ENABLED=true
uv run memory server --http

# 2. Add HTTP transport to Claude Code
claude mcp add --transport http memory-service http://localhost:8000/mcp

# โœ… Done! Claude Code automatically handles OAuth registration and team collaboration

๐Ÿ“– Complete Setup Guide: OAuth 2.1 Setup Guide


Traditional Setup Options

Universal Installer (Most Compatible):

# Clone and install with automatic platform detection
git clone https://github.com/doobidoo/mcp-memory-service.git
cd mcp-memory-service
python install.py

Smithery (Claude Desktop):

# Auto-install for Claude Desktop
npx -y @smithery/cli install @doobidoo/mcp-memory-service --client claude

Related MCP server: JauMemory MCP Server

โš ๏ธ v6.17.0+ Script Migration Notice

Updating from an older version? Scripts have been reorganized for better maintainability:

  • Recommended: Use python -m mcp_memory_service.server in your Claude Desktop config (no path dependencies!)

  • Alternative 1: Use uv run memory server with UV tooling

  • Alternative 2: Update path from scripts/run_memory_server.py to scripts/server/run_memory_server.py

  • Backward compatible: Old path still works with a migration notice

โš ๏ธ First-Time Setup Expectations

On your first run, you'll see some warnings that are completely normal:

  • "WARNING: Failed to load from cache: No snapshots directory" - The service is checking for cached models (first-time setup)

  • "WARNING: Using TRANSFORMERS_CACHE is deprecated" - Informational warning, doesn't affect functionality

  • Model download in progress - The service automatically downloads a ~25MB embedding model (takes 1-2 minutes)

These warnings disappear after the first successful run. The service is working correctly! For details, see our First-Time Setup Guide.

๐Ÿ Python 3.13 Compatibility Note

sqlite-vec may not have pre-built wheels for Python 3.13 yet. If installation fails:

  • The installer will automatically try multiple installation methods

  • Consider using Python 3.12 for the smoothest experience: brew install python@3.12

  • Alternative: Use ChromaDB backend with --storage-backend chromadb

  • See Troubleshooting Guide for details

๐ŸŽ macOS SQLite Extension Support

macOS users may encounter enable_load_extension errors with sqlite-vec:

  • System Python on macOS lacks SQLite extension support by default

  • Solution: Use Homebrew Python: brew install python && rehash

  • Alternative: Use pyenv: PYTHON_CONFIGURE_OPTS='--enable-loadable-sqlite-extensions' pyenv install 3.12.0

  • Fallback: Use ChromaDB backend: export MCP_MEMORY_STORAGE_BACKEND=chromadb

  • See Troubleshooting Guide for details

๐Ÿ“š Complete Documentation

๐Ÿ‘‰ Visit our comprehensive Wiki for detailed guides:

๐Ÿง  v7.1.0 Natural Memory Triggers (Latest)

  • Natural Memory Triggers v7.1.0 Guide - Intelligent automatic memory awareness

    • โœ… 85%+ trigger accuracy with semantic pattern detection

    • โœ… Multi-tier performance (50ms instant โ†’ 150ms fast โ†’ 500ms intensive)

    • โœ… CLI management system for real-time configuration

    • โœ… Git-aware context integration for enhanced relevance

    • โœ… Zero-restart installation with dynamic hook loading

๐Ÿ†• v7.0.0 OAuth & Team Collaboration

๐Ÿš€ Setup & Installation

๐Ÿง  Advanced Topics

โœจ Key Features

๐Ÿ” Enterprise Authentication & Team Collaboration ๐Ÿ†•

  • OAuth 2.1 Dynamic Client Registration - RFC 7591 & RFC 8414 compliant

  • Claude Code HTTP Transport - Zero-configuration team collaboration

  • JWT Authentication - Enterprise-grade security with scope validation

  • Auto-Discovery Endpoints - Seamless client registration and authorization

  • Multi-Auth Support - OAuth + API keys + optional anonymous access

๐Ÿง  Intelligent Memory Management

  • Semantic search with vector embeddings

  • Natural language time queries ("yesterday", "last week")

  • Tag-based organization with smart categorization

  • Memory consolidation with dream-inspired algorithms

๐Ÿ”— Universal Compatibility

  • Claude Desktop - Native MCP integration

  • Claude Code - HTTP transport + Memory-aware development with hooks

  • VS Code, Cursor, Continue - IDE extensions

  • 13+ AI applications - REST API compatibility

๐Ÿ’พ Flexible Storage

  • SQLite-vec - Fast local storage (recommended)

  • ChromaDB - Multi-client collaboration

  • Cloudflare - Global edge distribution

  • Automatic backups and synchronization

๐Ÿš€ Production Ready

  • Cross-platform - Windows, macOS, Linux

  • Service installation - Auto-start background operation

  • HTTPS/SSL - Secure connections with OAuth 2.1

  • Team collaboration - OAuth 2.1 with HTTP API support

๐Ÿ’ก Basic Usage

๐Ÿ”— Team Collaboration with OAuth (v7.0.0+)

# Start OAuth-enabled server for team collaboration
export MCP_OAUTH_ENABLED=true
uv run memory server --http

# Claude Code team members connect via HTTP transport
claude mcp add --transport http memory-service http://your-server:8000/mcp
# โ†’ Automatic OAuth discovery, registration, and authentication

๐Ÿง  Memory Operations

# Store a memory
uv run memory store "Fixed race condition in authentication by adding mutex locks"

# Search for relevant memories
uv run memory recall "authentication race condition"

# Search by tags
uv run memory search --tags python debugging

# Check system health (shows OAuth status)
uv run memory health

๐Ÿ”ง Configuration

Claude Desktop Integration

Recommended approach - Add to your Claude Desktop config (~/.claude/config.json):

{
  "mcpServers": {
    "memory": {
      "command": "python",
      "args": ["-m", "mcp_memory_service.server"],
      "env": {
        "MCP_MEMORY_STORAGE_BACKEND": "sqlite_vec"
      }
    }
  }
}

Alternative approaches:

// Option 1: UV tooling (if using UV)
{
  "mcpServers": {
    "memory": {
      "command": "uv",
      "args": ["--directory", "/path/to/mcp-memory-service", "run", "memory", "server"],
      "env": {
        "MCP_MEMORY_STORAGE_BACKEND": "sqlite_vec"
      }
    }
  }
}

// Option 2: Direct script path (v6.17.0+)
{
  "mcpServers": {
    "memory": {
      "command": "python",
      "args": ["/path/to/mcp-memory-service/scripts/server/run_memory_server.py"],
      "env": {
        "MCP_MEMORY_STORAGE_BACKEND": "sqlite_vec"
      }
    }
  }
}

Environment Variables

# Storage backend (sqlite_vec recommended)
export MCP_MEMORY_STORAGE_BACKEND=sqlite_vec

# Enable HTTP API
export MCP_HTTP_ENABLED=true
export MCP_HTTP_PORT=8000

# Security  
export MCP_API_KEY="your-secure-key"

๐Ÿ—๏ธ Architecture

โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”    โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”    โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
โ”‚   AI Clients    โ”‚    โ”‚  MCP Memory     โ”‚    โ”‚ Storage Backend โ”‚
โ”‚                 โ”‚    โ”‚  Service v7.0   โ”‚    โ”‚                 โ”‚
โ”‚ โ€ข Claude Desktopโ”‚โ—„โ”€โ”€โ–บโ”‚ โ€ข MCP Protocol  โ”‚โ—„โ”€โ”€โ–บโ”‚ โ€ข SQLite-vec    โ”‚
โ”‚ โ€ข Claude Code   โ”‚    โ”‚ โ€ข HTTP Transportโ”‚    โ”‚ โ€ข ChromaDB      โ”‚
โ”‚   (HTTP/OAuth)  โ”‚    โ”‚ โ€ข OAuth 2.1 Authโ”‚    โ”‚ โ€ข Cloudflare    โ”‚
โ”‚ โ€ข VS Code       โ”‚    โ”‚ โ€ข Memory Store  โ”‚    โ”‚ โ€ข Hybrid        โ”‚
โ”‚ โ€ข Cursor        โ”‚    โ”‚ โ€ข Semantic      โ”‚    โ”‚                 โ”‚
โ”‚ โ€ข 13+ AI Apps   โ”‚    โ”‚   Search        โ”‚    โ”‚                 โ”‚
โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜    โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜    โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜

๐Ÿ› ๏ธ Development

Project Structure

mcp-memory-service/
โ”œโ”€โ”€ src/mcp_memory_service/    # Core application
โ”‚   โ”œโ”€โ”€ models/                # Data models
โ”‚   โ”œโ”€โ”€ storage/               # Storage backends
โ”‚   โ”œโ”€โ”€ web/                   # HTTP API & dashboard
โ”‚   โ””โ”€โ”€ server.py              # MCP server
โ”œโ”€โ”€ scripts/                   # Utilities & installation
โ”œโ”€โ”€ tests/                     # Test suite
โ””โ”€โ”€ tools/                     # Development tools

Contributing

  1. Fork the repository

  2. Create a feature branch

  3. Make your changes with tests

  4. Submit a pull request

See CONTRIBUTING.md for detailed guidelines.

๐Ÿ†˜ Support

  • ๐Ÿ“– Documentation: Wiki - Comprehensive guides

  • ๐Ÿ› Bug Reports: GitHub Issues

  • ๐Ÿ’ฌ Discussions: GitHub Discussions

  • ๐Ÿ”ง Troubleshooting: Troubleshooting Guide

  • โœ… Configuration Validator: Run python scripts/validation/validate_configuration_complete.py to check your setup

  • ๐Ÿ”„ Backend Sync Tools: See scripts/README.md for Cloudflareโ†”SQLite sync

๐Ÿ“Š In Production

Real-world metrics from active deployments:

  • 750+ memories stored and actively used across teams

  • <500ms response time for semantic search (local & HTTP transport)

  • 65% token reduction in Claude Code sessions with OAuth collaboration

  • 96.7% faster context setup (15min โ†’ 30sec)

  • 100% knowledge retention across sessions and team members

  • Zero-configuration OAuth setup success rate: 98.5%

๐Ÿ† Recognition

  • Smithery Verified MCP Server

  • Glama AI Featured AI Tool

  • Production-tested across 13+ AI applications

  • Community-driven with real-world feedback and improvements

๐Ÿ“„ License

Apache License 2.0 - see LICENSE for details.


Ready to supercharge your AI workflow? ๐Ÿš€

๐Ÿ‘‰ Start with our Installation Guide or explore the Wiki for comprehensive documentation.

Transform your AI conversations into persistent, searchable knowledge that grows with you.

Related MCP Connectors

Related MCP Servers

  • F
    license
    A
    quality
    Not graded
    maintenance
    Provides long-term memory storage for AI assistants with semantic search, enabling persistent storage of preferences, decisions, and context with relationship tracking between memories.
    19
    -
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables persistent, searchable memory for AI assistants across platforms like Claude, ChatGPT, and Gemini, using semantic search and automatic deduplication.
    37 npm
    MIT