memory-bank

Memory Bank MCP is a Model Context Protocol server designed to help teams and individuals manage persistent memories, ideas, and code patterns across sessions. It offers core memory management features such as session-based thinking, persistent storage, collections, and revision tracking, plus a dedicated coding integration layer. The coding tools enable package discovery, reinvention prevention, code pattern storage, and specialized coding sessions, making it easier to reuse existing APIs and patterns rather than reinventing solutions. You can export sessions to Markdown or JSON, generate project structures, and perform context loading to resume ongoing work. Use the included session tools to start new memories, store insights, and analyze results, and leverage the coding integration tools to discover installed packages, validate usage against existing libraries, and store proven code snippets for reuse.

Prerequisites:

• Python 3.10 or newer
• uv (https://github.com/astral-sh/uv) installed

Installation steps:

1. Clone the repository or install the MCP server package as appropriate:

   • git clone https://github.com/spideynolove/memory-bank-mcp
   • cd memory-bank-mcp

2. Install and run using uv:

   • uv run main.py

3. Optional: install in development mode if you are contributing:

   • uv tool install .
   • uv pip install -e .

4. Verify installation:

   • uv run -c "import main; print('Installation successful')"

Prerequisites recap:

• Ensure Python 3.10+ is available on your system
• Install uv and verify it is accessible in your PATH
• Have network access for package discovery features when using the coding integration tools

Tips and notes:

• The server is designed to run with uv using the command: uv run main.py
• If you plan to use coding integration features, ensure your environment has commonly used Python packages installed (e.g., requests, fastapi) so the discovery and reinvention checks have data to compare against
• Use the session APIs to create memory sessions, store insights, and export sessions for sharing with teams
• When exporting, you can choose full dumps or filtered views depending on the project scope
• If you encounter issues with package discovery, verify your Python environment and PATH, and ensure uv is correctly installed