About Mem0 Memories
Mem0 Memories is an MCP server in the Social category: store and retrieve user-specific memories to maintain reliable long-term context. Search past memories to surface the most relevant details instantly. Organize preferences and facts per user for consistent, personalized interactions across sessions.
Install
git clone https://github.com/ssdavidai/mem0-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
Ask AI about Mem0 Memories
Powered by Claude · Grounded in docs
Security checks
- ✓README presentThe repository ships documentation.
5 checks have not been run yet.
README
Mem0 Memory MCP Server
A Model Context Protocol (MCP) server that provides memory storage and retrieval capabilities using Mem0. This server allows AI agents to store and search through memories, making it useful for maintaining context and making informed decisions based on past interactions.
Features
- Store memories with user-specific context
- Search through stored memories with relevance scoring
- Simple and intuitive API
- Built on the Model Context Protocol
- Automatic error handling
- Support for multiple user contexts
- Deployable on Smithery
Installation
Using npx (Recommended)
npx -y @mem0/mcp
Local Development
# Install dependencies
npm install
# Run development server with Smithery playground
npm run dev
# Build the project
npm run build
Configuration
The server requires a Mem0 API key to function. You can obtain one from Mem0 Dashboard.
For Smithery Deployment
When deploying on Smithery, users will be prompted to provide their API key through the configuration interface.
For Local Development
Create a .env file in the root directory:
MEM0_API_KEY=your-api-key-here
Available Tools
1. Add Memory (add-memory)
Store new memories with user-specific context.
Parameters:
content(string, required): The content to store in memoryuserId(string, required): User ID for memory storage
2. Search Memories (search-memories)
Search through stored memories to retrieve relevant information.
Parameters:
query(string, required): The search queryuserId(string, required): User ID for memory storage
Usage with MCP Clients
Cursor
- Open Cursor Settings
- Go to Features > MCP Servers
- Add the server configuration:
{
"mcpServers": {
"mem0-mcp": {
"command": "npx",
"args": ["-y", "@mem0/mcp"],
"env": {
"MEM0_API_KEY": "YOUR-API-KEY-HERE"
}
}
}
}
VS Code
Add to your User Settings (JSON):
{
"mcp": {
"inputs": [
{
"type": "promptString",
"id": "apiKey",
"description": "Mem0 API Key",
"password": true
}
],
"servers": {
"mem0-memory": {
"command": "npx",
"args": ["-y", "@mem0/mcp"],
"env": {
"MEM0_API_KEY": "${input:apiKey}"
}
}
}
}
}
Deployment on Smithery
This server is configured for deployment on Smithery:
- Push your code to GitHub
- Connect your repository to Smithery
- Deploy from the Deployments tab
The server will be available via Smithery's Streamable HTTP transport, allowing users to connect without installing dependencies locally.
Development
Project Structure
mem0-mcp/
├── src/
│ └── index.ts # Main server implementation
├── package.json # Dependencies and scripts
├── tsconfig.json # TypeScript configuration
├── tsup.config.ts # Build configuration
├── smithery.yaml # Smithery deployment config
└── README.md
Scripts
npm run dev- Start development server with Smithery playgroundnpm run build- Build the project using Smithery CLInpm run build:local- Build using tsup directlynpm run dev:local- Watch mode with tsupnpm start- Run the built server
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
MIT
README copy captured when this server was indexed; it may lag the repository. The original is authoritative.