abhinandanmishra1/mcp-server

GitHub PR Comment Resolver - MCP Server

A production-grade local MCP (Model Context Protocol) server that automates the resolution of GitHub PR review comments by fetching comments via GitHub API and generating structured prompts for LLM-based code resolution.

🎯 Features

• FastAPI-based MCP Server with RESTful endpoints
• GitHub API Integration to fetch PR comments and file content
• Multi-format Prompt Generation (Cursor, JSON, Markdown)
• Bot Filtering and user-specific comment processing
• File Context Enhancement with diff hunks and code snippets
• CLI Interface for command-line usage
• Background Processing for automated change application
• Production-ready with proper error handling, logging, and configuration

🚀 Quick Start

1. Installation

# Clone and setup
git clone <your-repo>
cd cursor-pr-fix

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

2. Configuration

# Copy environment template
cp .env.example .env

# Edit .env with your GitHub token
GITHUB_TOKEN=your_github_token_here

Get GitHub Token:

1. Go to GitHub Settings > Developer settings > Personal access tokens
2. Create new token with repo scope
3. Copy token to .env file

3. Usage Options

Option A: CLI (Recommended for first use)

# Generate Cursor-compatible prompt
python cli.py generate-prompt https://github.com/owner/repo/pull/123

# With options
python cli.py generate-prompt https://github.com/owner/repo/pull/123 \
  --format-type cursor \
  --skip-bots \
  --dry-run

# Apply changes directly (placeholder implementation)
python cli.py apply-changes https://github.com/owner/repo/pull/123 --dry-run

# Check status
python cli.py status

Option B: MCP Server

# Start server
python cli.py start-server

# Or directly
python server.py

Server will run on http://127.0.0.1:8000 with API docs at /docs

Option C: API Calls

# Generate prompt via API
curl -X POST "http://127.0.0.1:8000/generate-cursor-task" \
  -H "Content-Type: application/json" \
  -d '{
    "pr_url": "https://github.com/owner/repo/pull/123",
    "format_type": "cursor",
    "skip_bots": true
  }'

📁 Project Structure

cursor-pr-fix/
├── server.py              # FastAPI MCP server
├── cli.py                 # Command-line interface
├── requirements.txt       # Python dependencies
├── .env.example          # Environment variables template
├── handlers/
│   ├── __init__.py
│   └── github.py         # GitHub API interactions
├── prompt/
│   ├── __init__.py
│   └── generator.py      # Prompt generation logic
├── utils/
│   ├── __init__.py
│   └── file_manager.py   # File operations and change application
└── pr_prompts/           # Generated prompt files (auto-created)

🔧 Configuration

Environment Variables

API Endpoints

📋 Request/Response Format

Generate Prompt Request

{
  "pr_url": "https://github.com/owner/repo/pull/123",
  "dry_run": false,
  "only_user": "username",
  "skip_bots": true,
  "auto_apply": false,
  "format_type": "cursor"
}

Response

{
  "success": true,
  "message": "Generated prompt for 5 comments",
  "comments_found": 5,
  "prompt_file": "cursor_prompt_repo_123.txt",
  "changes_applied": [],
  "errors": []
}

🎨 Output Formats

1. Cursor Format (Default)

Optimized for Cursor IDE with:

• Structured markdown sections
• Code context with syntax highlighting
• Actionable suggestions
• Best practices guidelines

2. JSON Format

Structured data for programmatic processing:

{
  "task": "resolve_pr_comments",
  "metadata": { ... },
  "comments": [ ... ]
}

3. Markdown Format

Clean markdown for documentation or review.

🔄 Workflow Integration

With Cursor IDE

1. Generate Prompt:

   python cli.py generate-prompt <PR_URL>
   

2. Copy & Paste:

   • Open generated .txt file
   • Copy content to Cursor chat
   • Let LLM analyze and apply changes

3. Review Changes:

   • LLM will explain reasoning
   • Apply suggested modifications
   • Review diffs before committing

Automated Workflow

# Generate and apply in one step (when implemented)
python cli.py generate-prompt <PR_URL> --auto-apply

🛠️ Development

Adding Custom Handlers

1. New Comment Processors:

   # In handlers/custom.py
   class CustomHandler:
       async def process_comment(self, comment: Dict) -> Dict:
           # Custom logic
           return processed_comment
   

2. New Prompt Formats:

   # In prompt/generator.py
   async def _generate_custom_prompt(self, comments, pr_info):
       # Custom format implementation
       return formatted_prompt
   

Testing

# Test with dry run
python cli.py generate-prompt <PR_URL> --dry-run

# Check status
python cli.py status

# Test API
curl http://127.0.0.1:8000/status

🔐 Security

• GitHub tokens are stored in environment variables
• No sensitive data in logs
• Rate limiting respected for GitHub API
• CORS configured for local development only

📊 Logging

Logs include:

• API request/response details
• GitHub API interactions
• File operation results
• Error details with context

Configure via LOG_LEVEL environment variable.

🤝 Contributing

1. Fork the repository
2. Create feature branch
3. Add tests for new functionality
4. Submit pull request

📄 License

MIT License - see LICENSE file for details.

🆘 Troubleshooting

Common Issues

1. GitHub Token Errors:

   • Verify token has repo scope
   • Check token hasn't expired
   • Ensure token is in .env file

2. API Rate Limits:

   • GitHub API has rate limits
   • Server respects pagination
   • Consider GitHub Apps for higher limits

3. File Not Found:

   • Ensure PR branch files exist locally
   • Check file paths in comments match local structure

Debug Mode

python cli.py --verbose generate-prompt <PR_URL>

For more help, check the /docs endpoint when server is running.