Leverages FFmpeg to perform video editing operations through natural language commands, supporting trimming, merging, format conversion, speed adjustment, audio track addition, audio extraction, subtitle addition, and basic filters
Video Editor MCP Server
A powerful video editing MCP server that leverages FFmpeg to perform video editing operations through natural language commands.
Components
Tools
The server implements one main tool:
execute_ffmpeg
: Executes FFmpeg commands with progress tracking- Takes a command string as input
- Validates and executes FFmpeg operations
- Reports real-time progress during processing
- Handles errors and provides detailed feedback
- Supports all FFmpeg operations including:
- Trimming/cutting
- Merging videos
- Converting formats
- Adjusting speed
- Adding audio tracks
- Extracting audio
- Adding subtitles
- Basic filters (brightness, contrast, etc.)
Configuration
Prerequisites
- FFmpeg must be installed and accessible in your system PATH
- Python 3.9 or higher
- Required Python packages:
Installation
- Install FFmpeg if not already installed:
- Install the video editor package:
Claude Desktop Integration
Configure in your Claude Desktop config file:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Development
Building and Publishing
- Sync dependencies:
- Build package:
- Publish to PyPI:
Note: Set PyPI credentials via:
- Token:
--token
orUV_PUBLISH_TOKEN
- Or username/password:
--username
/UV_PUBLISH_USERNAME
and--password
/UV_PUBLISH_PASSWORD
Debugging
For the best debugging experience, use the MCP Inspector:
Example Usage
Once connected to Claude Desktop, you can make natural language requests like:
- "Trim video.mp4 from 1:30 to 2:45"
- "Convert input.mp4 to WebM format"
- "Speed up video.mp4 by 2x"
- "Merge video1.mp4 and video2.mp4"
- "Extract audio from video.mp4"
- "Add subtitles.srt to video.mp4"
The server will:
- Parse your request
- Generate the appropriate FFmpeg command
- Execute it with progress tracking
- Provide feedback on completion
Error Handling
The server includes robust error handling for:
- Invalid input files
- Malformed FFmpeg commands
- Runtime execution errors
- Progress tracking issues
All errors are reported back to the client with detailed messages for debugging.
Security Considerations
- Only processes files in explicitly allowed directories
- Validates FFmpeg commands before execution
- Sanitizes all input parameters
- Reports detailed error messages for security-related issues
Contributing
Contributions are welcome! Please follow these steps:
- Fork the repository
- Create your feature branch
- Make your changes
- Submit a pull request
This server cannot be installed
local-only server
The server can only run on the client's local machine because it depends on local resources.
Enables video editing using natural language commands powered by FFmpeg, supporting operations like trimming, merging, format conversion, and more with real-time progress tracking and error handling.
Related Resources
Related MCP Servers
- AsecurityFlicenseAqualityA Node.js server that enables video manipulation through natural language requests, including resizing videos to different resolutions (360p to 1080p) and extracting audio in various formats (MP3, AAC, WAV, OGG).Last updated -49427TypeScript
- AsecurityFlicenseAqualityEnables interaction with YouTube videos by extracting metadata, captions in multiple languages, and converting content to markdown with various templates.Last updated -1161TypeScript
- -securityAlicense-qualityA lightweight server that exposes FFmpeg's video processing capabilities to AI assistants through the Model Context Protocol (MCP), supporting operations like video format conversion, audio extraction, and adding watermarks.Last updated -27915TypeScriptMIT License
- AsecurityAlicenseAqualityAn MCP server providing video processing capabilities through FFmpeg, enabling dialog-based local video search, trimming, concatenation, and playback functionalities.Last updated -765PythonMIT License