PR-MCP-Server

Qehbr/PR-MCP-Server

3.1

If you are the rightful owner of PR-MCP-Server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

This project provides an intelligent PR agent that automates development tasks by analyzing code changes, monitoring CI/CD pipelines, and sending notifications.

This project gives you an intelligent PR (Pull Request) agent that automates common development tasks. It analyzes your code changes, monitors your CI/CD pipeline on GitHub Actions, and sends smart notifications to Slack.


Project Files

  • server.py: The main application. This is the MCP server that contains all the logic, including tools for analyzing Git repositories and sending Slack messages, and prompts for generating reports.
  • webhook_server.py: A simple web server that listens for events (like build failures) from GitHub Actions and saves them for the main server to analyze.
  • pyproject.toml: Defines the project's dependencies.
  • tests/test_server.py: Unit tests to verify the server's functionality.

How to Use It

  1. Install Dependencies: Open your terminal and run:

    uv sync
    
  2. Set Up Slack: Create a Slack webhook URL and set it as an environment variable.

    export SLACK_WEBHOOK_URL="[https://hooks.slack.com/services/](https://hooks.slack.com/services/)..."
    
  3. Configure GitHub: Set up a webhook in your GitHub repository to send events (like workflow_run) to the webhook_server.py. You'll need to expose your local server to the internet using a tool like ngrok or cloudflared.

  4. Run the Servers: You need to run both servers in two separate terminal windows.

    • Terminal 1 (Webhook Listener):
      python webhook_server.py
      
    • Terminal 2 (Main Server):
      uv run server.py
      

Your agent is now live. It will listen for GitHub events and you can interact with it using an MCP client to get reports and send notifications.