Mem0 Memory Server is an MCP-compatible memory layer that uses Mem0 (mem0.ai) to persistently store, search, and retrieve coding preferences and technical knowledge. It enables AI coding assistants to maintain context across sessions by remembering code snippets, implementation patterns, setup configurations, and best practices. Key features: - Store code snippets with comprehensive context including dependencies, language/framework versions, setup instructions, and documentation - Semantic search through stored coding preferences to find relevant implementations, solutions, and best practices - Retrieve all stored preferences to analyze patterns and ensure no relevant context is missed - SSE-based endpoint for integration with MCP-compatible clients like Cursor - Persistent memory system that runs as a decoupled process, allowing agents to connect, use, and disconnect as needed

MCP Server with Mem0 for Managing Coding Preferences

This demonstrates a structured approach for using an MCP server with mem0 to manage coding preferences efficiently. The server can be used with Cursor and provides essential tools for storing, retrieving, and searching coding preferences.

Installation

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

uv venv

3. Activate the virtual environment:

source .venv/bin/activate

4. Install the dependencies using uv:

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

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

MEM0_API_KEY=your_api_key_here

Usage

1. Start the MCP server:

uv run main.py

2. In Cursor, connect to the SSE endpoint, follow this doc for reference:

http://0.0.0.0:8080/sse

3. Open the Composer in Cursor and switch to Agent mode.

Demo with Cursor

https://github.com/user-attachments/assets/56670550-fb11-4850-9905-692d3496231c

Features

The server provides three main tools for managing code preferences:

1. add_coding_preference: Store code snippets, implementation details, and coding patterns with comprehensive context including: - 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 preferences to analyze patterns, review implementations, and ensure no relevant information is missed.

3. search_coding_preferences: Semantically search through stored coding preferences to find relevant: - Code implementations - Programming solutions - Best practices - Setup guides - Technical documentation

Why?

This implementation allows for a persistent coding preferences system that can be accessed via MCP. The SSE-based server can run as a process that agents connect to, use, and disconnect from whenever needed. This pattern fits well with "cloud-native" use cases where the server and clients can be decoupled processes on different nodes.

Server

By default, the server runs on 0.0.0.0:8080 but is configurable with command line arguments like:

uv run main.py --host  --port 

The server exposes an SSE endpoint at /sse that MCP clients can connect to for accessing the coding preferences management tools.