video-edit-mcp is a powerful Model Context Protocol (MCP) server designed for advanced video and audio editing operations. It enables MCP clients such as Claude Desktop and Cursor to perform comprehensive multimedia editing tasks through a standardized, unified interface.
Key Capabilities
Video Operations:
- Basic editing: trim, merge, resize, crop, rotate video
- Effects: speed control, fade in/out, grayscale, mirror
- Overlays: add text, images, or video overlays with transparency
- Format conversion: convert between different formats and control codecs
- Frame operations: extract frames, create video from images
Audio Operations:
- Audio processing: extract, trim, loop, concatenate audio
- Volume control: adjust levels, fade in/out effects
- Audio mixing: mix multiple audio tracks
- Integration: add audio to video, replace audio tracks
Download and Utilities:
- Video download: download from YouTube and other platforms
- File management: directory operations, file listing
- Path suggestions: get recommended download locations
Memory and Cleanup:
- Smart memory: no need to save intermediate files during chained operations
- Resource management: clear memory, inspect stored objects
- Efficient processing: keep objects in memory to support complex workflows
Operation Chaining Seamlessly chain multiple operations together without producing intermediate files. For example, process a video in the order of "trim → add audio → apply effects → add text", keeping everything in memory throughout for optimal performance.
Environment Requirements
- Python 3.10 or higher
- yt-dlp>=2023.1.6
- typing-extensions>=4.0.0
Installation and Setup
MCP Integration for Claude Desktop / Cursor:
- Ensure uv is installed; if not, it can be installed using the relevant PowerShell command
- Add the configuration to the MCP configuration file, 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 the project root directory
- Manual installation is also supported
Project Structure The project contains the corresponding directory and file organization (specific details are not listed in the material).
Example Usage The material provides an Example Usage section heading, but no specific example content is given, so it is not provided for now.
Future Enhancements and Contributions The project welcomes contributions in the following areas:
- Speech-to-text (STT): automatic subtitle generation and transcription
- Text-to-speech (TTS): AI voice synthesis 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: tracking and editing based on detected objects
- Content analysis: AI-driven content classification and tagging
Contribution process: Fork the repository; create a feature branch (git checkout -b feature/amazing-feature); commit your changes (git commit -m 'Add amazing feature'); push the branch (git push origin feature/amazing-feature); open a Pull Request.
License This project is licensed under the MIT License, see the LICENSE file for details.
