Mem0

🚀 Managing Coding Preference Settings with mem0's MCP Server

This demonstrates a structured approach to managing coding preferences by integrating the MCP server with mem0. The server can be used in conjunction with Cursor and offers utilities for storing, retrieving, and searching coding preference settings.

🚀 Quick Start

📦 Installation

1. Clone this repository.
2. Initialize the uv environment:

uv venv

3. Activate the virtual environment:

source .venv/bin/activate

4. Install dependencies using uv:

# Install in editable mode from pyproject.toml
uv pip install -e .

5. Update the .env file in the root directory and add your mem0 API key:

MEM0_API_KEY=your_api_key_here

💻 Usage

1. Start the MCP server:

uv run main.py

2. Connect to the SSE endpoint in Cursor, referring to this documentation:

http://0.0.0.0:8080/sse

3. Open Cursor's Composer and switch to Agent mode.

💻 Usage Examples

Basic Usage

Video Link

✨ Features

The server provides three main tools for managing code preferences:

1. add_coding_preference: Store code snippets, implementation details, and coding patterns, including complete context information:
   • Complete code with dependencies
   • Language/framework versions
   • Setup instructions
   • Documentation and comments
   • Example usage
   • Best practices
2. get_all_coding_preferences: Retrieve all stored coding preference settings to analyze patterns, review implementations, and ensure no relevant information is missed.
3. search_coding_preferences: Semantically search stored coding preference settings to find relevant content:
   • Code implementations
   • Programming solutions
   • Best practices
   • Setup guides
   • Technical documentation

🔧 Technical Details

This implementation allows for a persistent coding preference settings system accessible via MCP. The SSE-based server can run as a process for agents to connect to, use, and disconnect from on demand. This model is well-suited for "cloud-native" use cases, where the server and client can be decoupled processes on different nodes.

Server

By default, the server runs on 0.0.0.0:8080, but it can be configured via command-line arguments:

uv run main.py --host <your host> --port <your port>

The server exposes an SSE endpoint at /sse, through which MCP clients can access the coding preference management tools.