The MCP Provenance Monitor is a Python-based dashboard that tracks and displays provenance information for MCP servers published on npm or PyPI, sourcing data from the MCP registry. It includes a data collector module you can run in development mode to fetch provenance data and a lightweight web server component that serves the dashboard UI from the local web directory. To start, run the collector in development mode to begin gathering provenance information, and serve the web UI so you can view and interact with the dashboard locally.

Prerequisites:

• Python 3.8+ installed on your system
• git (to clone the repository)

1. Clone the repository: git clone https://github.com/letmaik/mcp-provenance-monitor.git cd mcp-provenance-monitor

2. Create and activate a virtual environment (recommended): python -m venv venv

   On Windows

   venv\Scripts\activate

   On Unix or macOS

   source venv/bin/activate

3. Install dependencies: pip install -r requirements.txt

4. Run the development collector and serve the web UI (from repository root): python -m collector.main --dev python -m http.server -d web

5. Open the dashboard in your browser at http://localhost:8000 (or the port shown by the http.server instruction).

Notes and tips:

• The monitor pulls data from the MCP registry and supports MCP servers published on npm or PyPI. If a server isn’t listed, it may not yet be in the registry.
• Data updates are refreshed daily; if you publish new provenance, allow up to a day for it to appear.
• The development command uses the collector module to fetch provenance data; the static web assets for the dashboard are served from the web directory via a simple HTTP server.
• If you need to adjust data sources or refresh cadence, modify the collector configuration or environment variables as needed in your local setup.
• In production, you would typically containerize or deploy the Python service alongside a static web server for the dashboard.