MCP-Mem0: Your Gateway to Long-Term Agent Memory π
About
MCP server for long term agent memory with Mem0. Also useful as a template to get you started building your own MCP server with Python!
Details
- Author
- yellnuts
- Downloads
- 340
- Categories
- AI, Database
Jump to
- Long-term memory storage and retrieval for agents
- Pythonβbased, easy to customize and extend
- Lightweight with minimal resource requirements
- Serves as a template for building new MCP servers
- Configurable memory expiry, logging, and port
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MCP-Mem0: Your Gateway to Long-Term Agent Memory πCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Clone the repository, install dependencies with pip install -r requirements.txt, and run python server.py. The server starts on http://localhost:5000 and exposes HTTP endpoints for creating, retrieving, and deleting memories. Configuration can be adjusted in config.json.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp-mem0: your gateway to long-term agent memory \ud83d\ude80": {
"mcp-mem0-yellnuts": {
"command": "python",
"args": [
"server.py"
]
}
}
}
}
McpServers
{
"mcp-mem0-yellnuts": {
"command": "python",
"args": [
"server.py"
]
}
}
MCP-Mem0: Your Gateway to Long-Term Agent Memory π
Welcome to the MCP-Mem0 repository! This project provides a robust server for managing long-term agent memory using Mem0. It also serves as a helpful template for anyone looking to build their own MCP server with Python.
Table of Contents
- Features
- Getting Started
- Installation
- Usage
- Contributing
- License
- Contact
Features β¨
- Long-Term Memory Management: Efficiently store and retrieve agent memories.
- Python-Based: Built with Python, making it easy to customize and extend.
- Template Structure: A great starting point for your own MCP server development.
- Lightweight: Minimal resource requirements for easy deployment.
Getting Started π
To get started with MCP-Mem0, you will need to download the latest release. Visit the Releases section to find the latest version. Download the file and execute it to set up your server.
Installation βοΈ
Follow these steps to install MCP-Mem0:
1. Clone the Repository:
git clone https://github.com/yellnuts/mcp-mem0.git
cd mcp-mem0
2. Install Dependencies:
Ensure you have Python 3.6 or higher installed. Use pip to install the required packages:
pip install -r requirements.txt
3. Run the Server:
After installing the dependencies, you can start the server with:
python server.py
4. Access the API:
Open your web browser and navigate to http://localhost:5000 to access the server.
Usage π
Once the server is running, you can interact with it using HTTP requests. Below are some example endpoints you can use:
- Create Memory:
POST /memory
Body:
{
"agent_id": "unique_agent_id",
"memory_data": "Your memory data here"
}
- Retrieve Memory:
GET /memory/{agent_id}
- Delete Memory:
DELETE /memory/{agent_id}
For more detailed API documentation, refer to the API.md file in the repository.
Contributing π€
We welcome contributions to MCP-Mem0! Hereβs how you can help:
1. Fork the Repository: Click the "Fork" button at the top right corner of the page.
2. Create a Branch:
git checkout -b feature/YourFeature
3. Make Changes: Implement your feature or fix.
4. Commit Your Changes:
git commit -m "Add your message here"
5. Push to the Branch:
git push origin feature/YourFeature
6. Open a Pull Request: Go to the original repository and click on "New Pull Request".
License π
This project is licensed under the MIT License. See the LICENSE file for more details.
Contact π¬
For any inquiries or support, please contact the maintainer:
- Name: [Your Name]
- Email: [your.email@example.com]
- GitHub: your-github-profile
Thank you for checking out MCP-Mem0! We hope you find it useful. For the latest updates and releases, donβt forget to check the Releases section again.

---
Advanced Configuration π§
MCP-Mem0 allows for advanced configurations to suit your specific needs. You can adjust settings in the config.json file located in the root directory. Here are some of the key configurations you can modify:
- Memory Expiry: Set how long memories should be retained.
- Logging Level: Adjust the verbosity of server logs.
- Port Configuration: Change the port number if needed.
Example Configuration
Hereβs an example of what your config.json might look like:
{
"memory_expiry": "30 days",
"logging_level": "info",
"port": 5000
}
Troubleshooting π οΈ
If you encounter issues while using MCP-Mem0, consider the following common problems:
- Server Not Starting: Ensure that all dependencies are installed correctly.
- API Errors: Check the request format and ensure the server is running.
- Memory Not Saving: Verify that the agent_id is unique and correctly formatted.
Roadmap πΊοΈ
We have exciting plans for future updates! Here are some features we aim to implement:
- User Authentication: Secure your memory management with user accounts.
- Data Visualization: Graphical representation of memory data.
- Multi-Agent Support: Handle multiple agents simultaneously.
Stay tuned for these features and more!
Community π¬
Join our community to share your experiences, ask questions, and get support:
- Discord: Join our Discord Server
- Forum: Visit our Forum
We encourage you to engage with other users and contribute to discussions.
Final Thoughts π
Thank you for exploring MCP-Mem0! We believe this tool will be a valuable asset for anyone working with agent memory management. Your feedback is essential, so feel free to reach out with suggestions or improvements.
For the latest updates, donβt forget to visit the Releases section again. Happy coding!
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



