Mem0 Mcp

Mem0 Mcp

What is Mem0 Mcp about?

Mem0 Mcp offers a lightweight server that enables agents to manage coding preferences—code snippets, implementation details, version information, documentation, and best‑practice guides—through the Model Context Protocol (MCP). The server persists these preferences using Mem0 and exposes them via a Server‑Sent Events (SSE) endpoint.

How to use Mem0 Mcp?

1. Clone the repository and set up a Python virtual environment with uv venv.
2. Activate the environment: source .venv/bin/activate.
3. Install the package in editable mode: uv pip install -e ..
4. Add your Mem0 API key to a .env file (MEM0_API_KEY=your_api_key_here).
5. Start the server: uv run main.py (default on 0.0.0.0:8080).
6. Connect a MCP‑compatible client (e.g., Cursor) to http://0.0.0.0:8080/sse and invoke the provided tools.

Key features of Mem0 Mcp

• add_coding_preference: Store complete code contexts, dependencies, version specs, setup steps, documentation, examples, and best practices.
• get_all_coding_preferences: Retrieve every stored preference for review or analysis.
• search_coding_preferences: Perform semantic search across preferences to locate relevant implementations, solutions, or documentation.
• Configurable host/port via CLI arguments (--host, --port).
• SSE endpoint (/sse) for real‑time interaction with MCP clients.

Use cases of Mem0 Mcp

• Centralised repository of team coding standards and reusable snippets.
• Contextual assistance for AI‑powered IDEs (e.g., Cursor) to fetch preferred patterns on demand.
• Automated onboarding: new developers query the server for setup guides and best‑practice code.
• Continuous learning: agents enrich the knowledge base with newly discovered solutions.

FAQ

Q: Which language/runtime is required? A: Python (managed via uv).

Q: How is authentication handled? A: The server uses a Mem0 API key defined in the .env file.

Q: Can I change the listening port? A: Yes, run uv run main.py --host <host> --port <port>.

Q: Is the server compatible with other MCP clients? A: Any client that can connect to an SSE endpoint and follow the MCP specification can interact with the tools provided.

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 <your host> --port <your port>

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