MCP Memory Service
Offers Cloudflare as a global edge distribution storage backend for memory data, enabling fast access worldwide.
Integrates Git-aware context into memory triggers, using repository history to enhance relevance and accuracy.
Supports SQLite-vec as a local storage backend for fast semantic memory search with vector embeddings.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Memory Servicesave that my favorite restaurant is Thai"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Memory Service
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.
π Quick Start (2 minutes)
π§ v7.1.0: Natural Memory Triggers for Claude Code
π€ 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
# β
Done! Claude Code now automatically detects when you need memory contextπ Complete Guide: Natural Memory Triggers v7.1.0
π v7.0.0: OAuth 2.1 & Claude Code HTTP Transport
π 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
# β
Done! Claude Code automatically handles OAuth registration and team collaborationπ 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.pySmithery (Claude Desktop):
# Auto-install for Claude Desktop
npx -y @smithery/cli install @doobidoo/mcp-memory-service --client claudeRelated MCP server: BuildAutomata Memory MCP Server
β οΈ 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.serverin your Claude Desktop config (no path dependencies!)Alternative 1: Use
uv run memory serverwith UV toolingAlternative 2: Update path from
scripts/run_memory_server.pytoscripts/server/run_memory_server.pyBackward compatible: Old path still works with a migration notice
β οΈ 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.
π 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@3.12Alternative: Use ChromaDB backend with
--storage-backend chromadbSee Troubleshooting Guide for details
π 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 && rehashAlternative: Use pyenv:
PYTHON_CONFIGURE_OPTS='--enable-loadable-sqlite-extensions' pyenv install 3.12.0Fallback: Use ChromaDB backend:
export MCP_MEMORY_STORAGE_BACKEND=chromadbSee Troubleshooting Guide for details
π Complete Documentation
π Visit our comprehensive Wiki for detailed guides:
π§ v7.1.0 Natural Memory Triggers (Latest)
Natural Memory Triggers v7.1.0 Guide - Intelligent automatic memory awareness
β 85%+ trigger accuracy with semantic pattern detection
β Multi-tier performance (50ms instant β 150ms fast β 500ms intensive)
β CLI management system for real-time configuration
β Git-aware context integration for enhanced relevance
β Zero-restart installation with dynamic hook loading
π v7.0.0 OAuth & Team Collaboration
π OAuth 2.1 Setup Guide - NEW! Complete OAuth 2.1 Dynamic Client Registration guide
π Integration Guide - Claude Desktop, Claude Code HTTP transport, VS Code, and more
π‘οΈ Advanced Configuration - Updated! OAuth security, enterprise features
π Setup & Installation
π Installation Guide - Complete installation for all platforms and use cases
π₯οΈ Platform Setup Guide - Windows, macOS, and Linux optimizations
β‘ Performance Optimization - Speed up queries, optimize resources, scaling
π§ Advanced Topics
π¨βπ» Development Reference - Claude Code hooks, API reference, debugging
π§ Troubleshooting Guide - Updated! OAuth troubleshooting + common issues
β FAQ - Frequently asked questions
π Examples - Practical code examples and workflows
β¨ Key Features
π Enterprise Authentication & Team Collaboration π
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
π§ 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
π 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
πΎ Flexible Storage
SQLite-vec - Fast local storage (recommended)
ChromaDB - Multi-client collaboration
Cloudflare - Global edge distribution
Automatic backups and synchronization
π 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
π‘ Basic Usage
π 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
# β Automatic OAuth discovery, registration, and authenticationπ§ 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 healthπ§ 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"ποΈ Architecture
βββββββββββββββββββ βββββββββββββββββββ βββββββββββββββββββ
β AI Clients β β MCP Memory β β Storage Backend β
β β β Service v7.0 β β β
β β’ Claude DesktopβββββΊβ β’ MCP Protocol βββββΊβ β’ SQLite-vec β
β β’ Claude Code β β β’ HTTP Transportβ β β’ ChromaDB β
β (HTTP/OAuth) β β β’ OAuth 2.1 Authβ β β’ Cloudflare β
β β’ VS Code β β β’ Memory Store β β β’ Hybrid β
β β’ Cursor β β β’ Semantic β β β
β β’ 13+ AI Apps β β Search β β β
βββββββββββββββββββ βββββββββββββββββββ βββββββββββββββββββπ οΈ Development
Project Structure
mcp-memory-service/
βββ src/mcp_memory_service/ # Core application
β βββ models/ # Data models
β βββ storage/ # Storage backends
β βββ web/ # HTTP API & dashboard
β βββ server.py # MCP server
βββ scripts/ # Utilities & installation
βββ tests/ # Test suite
βββ tools/ # Development toolsContributing
Fork the repository
Create a feature branch
Make your changes with tests
Submit a pull request
See CONTRIBUTING.md for detailed guidelines.
π Support
π Documentation: Wiki - Comprehensive guides
π Bug Reports: GitHub Issues
π¬ Discussions: GitHub Discussions
π§ Troubleshooting: Troubleshooting Guide
β Configuration Validator: Run
python scripts/validation/validate_configuration_complete.pyto check your setupπ Backend Sync Tools: See scripts/README.md for CloudflareβSQLite sync
π 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 β 30sec)
100% knowledge retention across sessions and team members
Zero-configuration OAuth setup success rate: 98.5%
π Recognition
Verified MCP Server
Featured AI Tool
Production-tested across 13+ AI applications
Community-driven with real-world feedback and improvements
π License
Apache License 2.0 - see LICENSE for details.
Ready to supercharge your AI workflow? π
π Start with our Installation Guide or explore the Wiki for comprehensive documentation.
Transform your AI conversations into persistent, searchable knowledge that grows with you.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/alphaplapplap/mcp-memory-service'
If you have feedback or need assistance with the MCP directory API, please join our Discord server