Mem0 MCP Server
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Mem0 MCP Server with Anthropic Claude
A local Mem0 memory system configured to work with Anthropic's Claude API and MCP (Model Context Protocol).
Features
✅ Vector storage with Qdrant
✅ Graph database with Neo4j (to be configured)
✅ Metadata storage with PostgreSQL
✅ Anthropic Claude 3.5 Sonnet integration
✅ MCP server for Claude Code integration
Related MCP server: claude-memory
Prerequisites
Docker and Docker Compose
Python 3.12+
Anthropic API key (Claude subscription)
Quick Start
Clone the repository
git clone <your-repo-url>
cd mem0-setupSet up environment variables
cp .env.example .env
# Edit .env and add your MEM0_ANTHROPIC_KEYStart the databases
docker compose up -dInstall Python dependencies
pip install -r requirements.txtRun the Mem0 server
source .env
python3 mem0_server.pyThe server will be available at http://localhost:8765
Architecture
Qdrant: Vector database for semantic search
Neo4j: Graph database for relationship storage (optional)
PostgreSQL: Metadata and configuration storage
FastAPI: REST API server
MCP: Model Context Protocol integration
Configuration
The system uses MEM0_ANTHROPIC_KEY instead of ANTHROPIC_API_KEY to avoid conflicts with Claude's own authentication.
API Endpoints
GET /health- Health checkPOST /memories- Add a memoryPOST /memories/search- Search memoriesGET /memories- Get all memoriesPUT /memories/{memory_id}- Update a memoryDELETE /memories/{memory_id}- Delete a memory
MCP Integration
For Claude Code integration, add to your .mcp.json:
{
"mcpServers": {
"mem0": {
"command": "python3",
"args": ["/path/to/mem0_stdio_mcp.py"]
}
}
}License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Private persistent memory for Claude, ChatGPT & Gemini via MCP - semantic search, zero-code setup.
Persistent memory for AI agents across Claude, ChatGPT and any MCP client.
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceGives AI persistent personal memory with hybrid search, temporal decay, and knowledge graph. Works with Claude and any MCP client.12 npm10MIT
- AlicenseNot gradedqualityCmaintenanceA 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.64 npm5MIT
- AlicenseNot gradedqualityDmaintenancePersistent memory with semantic search for Claude and MCP-compatible clients, storing context that survives conversations and can be retrieved intelligently.1MIT
- AlicenseAqualityAmaintenanceMCP server providing persistent memory for AI applications, enabling Claude to store and recall memories with hybrid search and knowledge graph.667MIT