---
title: MCP GitHub PR Opportunity Server
emoji: 🔍
colorFrom: blue
colorTo: indigo
sdk: gradio
sdk_version: 5.33.1
app_file: app.py
pinned: false
tag: 
  - mcp-server-track
  - agent-demo-track
license: mit
---
# Video Link: https://drive.google.com/file/d/1FaYPqtoYWmUBsjiSFexPNyPARvFsixsh/view?usp=sharing

# MCP GitHub PR Opportunity Server

A Gradio-based MCP server that searches GitHub repositories for possible PR opportunities (open issues labeled 'good first issue' or 'help wanted'), supporting search by keyword and topic, with authentication.

## Features
- Search GitHub repos by keyword and topic
- Find open issues labeled 'good first issue' or 'help wanted'
- Supports GitHub authentication via token
- Gradio MCP server for LLM integration
- Interactive web interface
- Compatible with n8n workflows

## Local Setup

1. **Clone the repo and install dependencies:**
    ```bash
    cd mcp_github_server
    pip install -r requirements.txt
    ```

2. **Configure GitHub Token:**
    - Set `GITHUB_TOKEN` in your environment variables, or
    - Enter the token in the web interface

3. **Run the server:**
    ```bash
    python app.py
    ```

## Hugging Face Spaces Deployment

1. **Create a new Space:**
   - Go to [Hugging Face Spaces](https://huggingface.co/spaces)
   - Click "Create new Space"
   - Choose "Gradio" as the SDK
   - Name your space (e.g., "mcp-github-pr-server")

2. **Configure Environment Variables:**
   - In your Space settings, add `GITHUB_TOKEN` as a secret
   - Set your GitHub token as the value

3. **Deploy:**
   - Push your code to the Space repository
   - Hugging Face will automatically build and deploy your application

## Using with MCP Clients

Add this configuration to your MCP client (e.g., Claude Desktop, Cursor, or Cline):

```json
{
  "mcpServers": {
    "github-pr-finder": {
      "url": "https://akinyemiar-mcp-github-pr-server.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## Using with n8n

1. **Add HTTP Request Node:**
   - In your n8n workflow, add an "HTTP Request" node
   - Set the URL to your Hugging Face Space URL (e.g., `https://akinyemiar-mcp-github-pr-server.hf.space/api/predict`)
   - Set Method to POST
   - Add Headers:
     ```
     Content-Type: application/json
     ```
   - Set Body to JSON:
     ```json
     {
       "data": [
         "fastapi",
         "python",
         5,
         1,
         "YOUR_GITHUB_TOKEN"
       ]
     }
     ```

2. **Process Response:**
   - The response will contain opportunities and total_count
   - Use n8n's "Set" node to process the response data
   - Add additional nodes to handle the opportunities as needed

## API Usage

The server provides both a web interface and an API endpoint at `/api/predict`. The API accepts POST requests with the following parameters:

```json
{
  "data": [
    "keyword",     // optional
    "topic",       // optional
    "per_page",    // default: 5
    "page",        // default: 1
    "token"        // GitHub token
  ]
}
```

Response:
```json
{
  "data": [
    {
      "opportunities": [
        {
          "repo_name": "tiangolo/fastapi",
          "repo_url": "https://github.com/tiangolo/fastapi",
          "issue_title": "Add more examples",
          "issue_url": "https://github.com/tiangolo/fastapi/issues/1234",
          "issue_labels": ["good first issue"],
          "issue_body": "Please add more examples to the docs..."
        }
      ],
      "total_count": 123
    }
  ]
}
```

## License
MIT