Video Edit MCP

🚀 Video Edit MCP Server 🎬

A powerful Model Context Protocol (MCP) server tailored for advanced video and audio editing operations. It allows MCP clients, such as Claude Desktop and Cursor, to carry out comprehensive multimedia editing tasks via a standardized and unified interface.

Demo Video

🚀 Quick Start

This server empowers MCP clients to perform comprehensive multimedia editing tasks through a standardized and unified interface. Dive into the world of video and audio editing with the Video Edit MCP Server!

✨ Features

🎥 Video Operations

• Basic Editing: Trim, merge, resize, crop, and rotate videos.
• Effects: Control speed, apply fade in/out, convert to grayscale, and mirror videos.
• Overlays: Add text, images, or video overlays with adjustable transparency.
• Format Conversion: Convert between different formats with codec control.
• Frame Operations: Extract frames from videos and create videos from images.

🎵 Audio Operations

• Audio Processing: Extract, trim, loop, and concatenate audio.
• Volume Control: Adjust audio levels and apply fade in/out effects.
• Audio Mixing: Combine multiple audio tracks.
• Integration: Add audio to videos and replace soundtracks.

📥 Download & Utilities

• Video Download: Download videos from YouTube and other platforms.
• File Management: Perform directory operations and list files.
• Path Suggestions: Get recommended download locations.

🧹 Memory & Cleanup

• Smart Memory: Chain operations without saving intermediate files.
• Resource Management: Clear memory and check stored objects.
• Efficient Processing: Keep objects in memory for complex workflows.

🔗 Operation Chaining

Seamlessly chain multiple operations without creating intermediate files. Process your video through multiple steps (e.g., trim → add audio → apply effects → add text) while keeping everything in memory for optimal performance.

📦 Installation

For Claude Desktop / Cursor MCP Integration

Ensure that uv is installed. If not, install it using the following PowerShell command:

powershell -ExecutionPolicy Bypass -Command "irm https://astral.sh/uv/install.ps1 | iex"

Add this configuration to your MCP configuration file:

{
  "mcpServers": {
    "video_editing": {
      "command": "uvx",
      "args": [
        "--python",
        "3.11",
        "video-edit-mcp"
      ]
    }
  }
}

Configuration file locations:

• Claude Desktop (Windows): %APPDATA%/Claude/claude_desktop_config.json
• Claude Desktop (macOS): ~/Library/Application Support/Claude/claude_desktop_config.json
• Cursor: .cursor/mcp.json in your project root

Manual Installation

git clone https://github.com/Aditya2755/video-edit-mcp.git
cd video-edit-mcp
pip install -r requirements.txt
pip install -e .

📚 Documentation

🏗️ Project Structure

video_edit_mcp/
├── src/
│   └── video_edit_mcp/
│       ├── __init__.py
│       ├── main.py                 # MCP server implementation  
│       ├── video_operations.py     # Video editing tools
│       ├── audio_operations.py     # Audio processing tools
│       ├── download_utils.py       # Download functionality
│       ├── util_tools.py          # Memory & utility tools
│       ├── utils.py               # Utility functions
│     
├── pyproject.toml                 # Project configuration
├── requirements.txt               # Dependencies
├── uv.lock                        # Lock file
├── LICENSE                        # MIT License
├── MANIFEST.in                    # Manifest file
└── README.md

💻 Usage Examples

Basic Usage

# Chain operations without intermediate files
video_info = get_video_info("input.mp4")
trimmed = trim_video("input.mp4", 10, 60, return_path=False)  # Keep in memory
with_audio = add_audio(trimmed, "background.mp3", return_path=False)  
final = add_text_overlay(with_audio, "Hello World", x=100, y=50, return_path=True)

🚀 Future Enhancements & Contributions

We welcome contributions in these exciting areas:

🤖 AI-Powered Features

• Speech-to-Text (STT): Automatic subtitle generation and transcription.
• Text-to-Speech (TTS): AI voice synthesis for narration.
• Audio Enhancement: AI-based noise reduction and audio quality improvement.
• Smart Timestamps: Automatic scene detection and chapter generation.
• Face Tracking: Advanced face detection and tracking for automatic editing.
• Object Recognition: Track and edit based on detected objects.
• Content Analysis: AI-powered content categorization and tagging.

🤝 Contributing

1. Fork the repository.
2. Create a feature branch: git checkout -b feature/amazing-feature.
3. Commit your changes: git commit -m 'Add amazing feature'.
4. Push to the branch: git push origin feature/amazing-feature.
5. Open a Pull Request.

📄 License

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