ffmpeg-mcp
About
A Python package for media processing using FFmpeg and FastMCP.
Details
- Author
- yubraaj11
- Categories
- Other, Media
Jump to
Setup
Install ffmpeg-mcp in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/yubraaj11/ffmpeg-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
Edit video and audio by just talking to your AI assistant.
FFmpeg is incredibly powerful and incredibly hard to remember.ffmpeg-mcphands that power to your AI assistant so you can say what you want in plain English:
"Grab the first 10 seconds ofdemo.mov, scale it to 1080p, slap my logo in the top-right corner, and turn it into a GIF."
…and the model orchestrates the right tools for you. Each tool is a small, validated Python function — easy to read, reuse, and extend.
- 🗣️Natural-language video editing— works in any MCP client (Claude Desktop, Cursor, Cline, …)
- 🧱12 focused tools— composable building blocks instead of one giant black box
- ✅Input validation built in— paths are checked for existence, emptiness, and validity before FFmpeg runs
- 🧩Hackable— add a new tool by writing one function and registering it
?marks optional parameters.concat_clips_with_transitionsupports many transitions —fade,wipeleft,slideup,circlecrop,dissolve,pixelize,radial, anddozens more.
- Python 3.12+
- FFmpeginstalled and on yourPATH(providesffmpeg+ffprobe)
- uvpackage manager
git clone https://github.com/yubraaj11/ffmpeg-mcp.git cd ffmpeg-mcp uv sync --frozen
Point your client at the server using the snippets below. Replace/path/to/ffmpeg-mcpwith theabsolute pathto your clone.
{ "mcpServers": { "ffmpeg-mcp": { "command": "uv", "args": ["--directory", "/path/to/ffmpeg-mcp/ffmpeg_mcp", "run", "main.py"], "env": { "PYTHONPATH": "/path/to/ffmpeg-mcp" } } } }
{ "mcpServers": { "ffmpeg-mcp": { "autoApprove": [], "disabled": false, "timeout": 60, "command": "uv", "args": ["--directory", "/path/to/ffmpeg-mcp/ffmpeg_mcp", "run", "main.py"], "env": { "PYTHONPATH": "/path/to/ffmpeg-mcp" }, "transportType": "stdio" } } }
3. Restart your client and start editing
"Extract 5 evenly-spaced frames fromintro.mp4."
"Make a 3-second GIF fromclip.movstarting at 12s."
"Concatenatea.mp4,b.mp4, andc.mp4with a 1-secondwipelefttransition between them."
Processed files are written underffmpeg_mcp/processed_elements/.
ffmpeg_mcp/ ├── main.py # MCP server entry point — registers all tools ├── services/ # one module per tool ├── configs/ # colored logging setup └── exceptions/ # structured error messages utils/ # validation decorators & helpers
Every tool returns either the output file path or a structured JSON error (status,error_type,message,time), so failures are easy for the model to read and recover from.
Contributions are very welcome! Adding a tool is roughly:
- Write a function inffmpeg_mcp/services/your_tool.py.
- Export it fromffmpeg_mcp/services/__init__.py.
- Register it inmain.pywithmcp.tool(name_or_fn=your_tool).
Please run the linter before opening a PR:
Found a bug or have an idea?Open an issue— and if this project saves you from anotherffmpegman-page dive, consider leaving a ⭐.
- fastmcp— the MCP server framework
- ffmpeg-python— Python bindings for FFmpeg
- pydantic— data validation
- colorlog— colored logs
A powerful video editing server using ffmpeg-python to process external video files.
Official MCP server for Very Good FFmpeg
All-in-one AI creative studio — generate videos, images, audio in 11 Indian languages, and 3D models via MCP. Hosted at mcp.arcframe.ai.
A server for creating fast and free lipsync videos for digital avatars, supporting both realistic and cartoon styles.
Batch audio processing and optimization using FFmpeg. Modify sample rate, bitrate, volume, channels, and apply effects.
Cast local files and media URLs to Chromecast and DLNA/UPnP devices on your LAN.
A server for media processing, offering powerful video and image manipulation using FFmpeg and ImageMagick.
Create AI music videos and audio-reactive visuals from songs through MCP.
Turn any language model into a multimodal powerhouse that can generate images, music, videos and more on the fly. Rostro's tools are designed to be used by language models from the ground up, expanding capabilities with minimal context bloat.
The World's First AI Music MCP Beyond images and video, your agent can now generate music.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
