- Notifications
You must be signed in to change notification settings - Fork8
mem0ai/mem0-mcp
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
This demonstrates a structured approach for using anMCP server withmem0 to manage coding preferences efficiently. The server can be used with Cursor and provides essential tools for storing, retrieving, and searching coding preferences.
- Clone this repository
- Initialize the
uv
environment:
uv venv
- Activate the virtual environment:
source .venv/bin/activate
- Install the dependencies using
uv
:
# Install in editable mode from pyproject.tomluv pip install -e.
- Update
.env
file in the root directory with your mem0 API key:
MEM0_API_KEY=your_api_key_here
- Start the MCP server:
uv run main.py
- In Cursor, connect to the SSE endpoint, follow thisdoc for reference:
http://0.0.0.0:8080/sse
- Open the Composer in Cursor and switch to
Agent
mode.
mcp_demo.mp4
The server provides three main tools for managing code preferences:
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
get_all_coding_preferences
: Retrieve all stored coding preferences to analyze patterns, review implementations, and ensure no relevant information is missed.search_coding_preferences
: Semantically search through stored coding preferences to find relevant:- Code implementations
- Programming solutions
- Best practices
- Setup guides
- Technical documentation
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.
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.