giteamcp/README.md

# MCP Server - AI-Powered Code Editor

A comprehensive server that automatically clones Gitea repositories, analyzes code with AI models (Gemini/OpenAI), applies intelligent code changes, and commits them back to the repository.

## 🚀 Features

- **Repository Management**: Clone repositories from Gitea with authentication
- **AI-Powered Analysis**: Use Gemini CLI or OpenAI to analyze and edit code
- **Model Selection**: Choose specific AI models (e.g., gemini-1.5-pro, gpt-4)
- **Real-time Progress Tracking**: Web interface with live status updates
- **Modern UI**: Beautiful, responsive frontend with progress indicators
- **Background Processing**: Asynchronous task processing with status monitoring
- **Comprehensive Logging**: Full logging to both console and file
- **Docker Support**: Easy deployment with Docker and docker-compose

## 📋 Prerequisites

- Python 3.8+
- Git
- API keys for AI models (Gemini or OpenAI)

## 🛠️ Installation

### Option 1: Docker (Recommended)

1. **Clone the repository**
   ```bash
   git clone <your-repo-url>
   cd mcp-server
   ```

2. **Build and run with Docker Compose**
   ```bash
   docker-compose up --build
   ```

3. **Or build and run manually**
   ```bash
   docker build -t mcp-server .
   docker run -p 8000:8000 mcp-server
   ```

### Option 2: Local Installation

1. **Clone the repository**
   ```bash
   git clone <your-repo-url>
   cd mcp-server
   ```

2. **Install Python dependencies**
   ```bash
   pip install -r requirements.txt
   ```

3. **Install Gemini CLI (if using Gemini)**
   ```bash
   # Download from GitHub releases
   curl -L https://github.com/google/generative-ai-go/releases/latest/download/gemini-linux-amd64 -o /usr/local/bin/gemini
   chmod +x /usr/local/bin/gemini
   ```

4. **Start the server**
   ```bash
   python main.py
   # or
   python start.py
   ```

## 🚀 Usage

### Using the Web Interface

1. Open your browser and navigate to `http://localhost:8000`
2. Fill in the repository details:
   - **Gitea Repository URL**: Your repository URL (e.g., `http://157.66.191.31:3000/user/repo.git`)
   - **Gitea Token**: Your Gitea access token (get from Settings → Applications → Generate new token)
   - **AI Model**: Choose between Gemini CLI or OpenAI
   - **Model Name**: Specify the exact model (e.g., `gemini-1.5-pro`, `gpt-4`)
   - **API Key**: Your AI model API key
   - **Prompt**: Describe what changes you want to make to the code

3. Click "Process Repository" and monitor the progress

### API Endpoints

- `GET /` - Web interface
- `POST /process` - Start repository processing
- `GET /status/{task_id}` - Get processing status
- `GET /health` - Health check

## 🔧 Configuration

### Environment Variables

| Variable | Description | Default |
|----------|-------------|---------|
| `HOST` | Server host | `0.0.0.0` |
| `PORT` | Server port | `8000` |

### Supported AI Models

**Gemini Models:**
- `gemini-1.5-pro` (recommended)
- `gemini-1.5-flash`
- `gemini-1.0-pro`

**OpenAI Models:**
- `gpt-4`
- `gpt-4-turbo`
- `gpt-3.5-turbo`

### Supported File Types

The system analyzes and can modify:
- Python (`.py`)
- JavaScript (`.js`, `.jsx`)
- TypeScript (`.ts`, `.tsx`)
- HTML (`.html`)
- CSS (`.css`)
- JSON (`.json`)
- Markdown (`.md`)

## 📁 Project Structure

```
mcp-server/
├── main.py              # FastAPI application
├── requirements.txt     # Python dependencies
├── Dockerfile          # Docker configuration
├── docker-compose.yml  # Docker Compose configuration
├── README.md           # This file
├── templates/
│   └── index.html      # Frontend template
├── static/
│   ├── style.css       # Frontend styles
│   └── script.js       # Frontend JavaScript
└── logs/               # Log files (created by Docker)
```

## 🔄 How It Works

1. **Repository Cloning**: Authenticates with Gitea and clones the repository
2. **AI Analysis**: Sends code and prompt to selected AI model
3. **Code Modification**: Applies AI-suggested changes to the codebase
4. **Commit & Push**: Commits changes and pushes back to Gitea

## 🎯 Example Prompts

- "Add error handling to all API endpoints"
- "Optimize database queries for better performance"
- "Add comprehensive logging throughout the application"
- "Refactor the authentication system to use JWT tokens"
- "Add unit tests for all utility functions"

## 📊 Logging

The server provides comprehensive logging:
- **Console Output**: Real-time logs in the terminal
- **File Logging**: Logs saved to `mcp_server.log`
- **Task-specific Logging**: Each task has detailed logging with task ID

### Viewing Logs

**Docker:**
```bash
# View container logs
docker logs <container_id>

# Follow logs in real-time
docker logs -f <container_id>
```

**Local:**
```bash
# View log file
tail -f mcp_server.log
```

## 🔒 Security Considerations

- API keys are sent from frontend and not stored
- Use HTTPS in production
- Implement proper authentication for the web interface
- Regularly update dependencies
- Monitor API usage and costs

## 🐛 Troubleshooting

### Common Issues

1. **Repository cloning fails**
   - Verify Gitea token is valid and has repository access
   - Check repository URL format
   - Ensure repository exists and is accessible
   - Make sure token has appropriate permissions (read/write)

2. **AI model errors**
   - Verify API keys are correct
   - Check model name spelling
   - Ensure internet connectivity

3. **Gemini CLI not found**
   - Install Gemini CLI: `curl -L https://github.com/google/generative-ai-go/releases/latest/download/gemini-linux-amd64 -o /usr/local/bin/gemini && chmod +x /usr/local/bin/gemini`

### Logs

Check the logs for detailed error messages and processing status:
- **Frontend**: Real-time logs in the web interface
- **Backend**: Console and file logs with detailed information

## 🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

## 📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

## 🆘 Support

For issues and questions:
1. Check the troubleshooting section
2. Review the logs in the web interface and console
3. Create an issue in the repository

---

**Note**: This tool modifies code automatically. Always review changes before deploying to production environments.