About videokit
videokit is a CLI and stdio MCP server for processing local video files with ffmpeg and ffprobe. It probes media properties and supports frame, thumbnail, audio, trim, transcode, and resize operations; it relies on binaries installed on the host.
Key features
- 01Inspect duration, dimensions, codecs, and format
- 02Extract thumbnails and frame sequences
- 03Extract audio tracks
- 04Trim video segments
- 05Transcode and resize video
Use cases
- 01Check a local video's technical properties
- 02Create thumbnails or sampled frames
- 03Extract audio or trim a clip
- 04Convert a video format or dimensions
MCP support
The stdio MCP server exposes tools to probe local videos, extract thumbnails, frames, and audio, and trim, transcode, or resize files.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
7Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| file_path | string | Yes | Path to the local video file to probe. |
Details
From the project READMEvideokit
Local video file tools as a CLI and a stdio MCP server in one bin. Probe a video for duration, dimensions and codecs; extract a thumbnail, frames or the audio track; trim, transcode and resize.
All work is built as ffmpeg/ffprobe argument arrays (execFile, never a shell string) behind an injectable executor, and probe results are parsed from ffprobe's JSON output — fields a file does not carry come back as null, never invented. This package bundles no ffmpeg: host runs use the host's binaries, and when they are absent the spawn error (ENOENT) is the tool error.
Install
npx -y @reneturcios/videokit mcp
CLI
videokit mcp
videokit probe <file>
videokit thumbnail <file> <output> [timestamp-seconds]
videokit audio <file> <output>
videokit trim <file> <output> <start-seconds> [duration-seconds]
videokit resize <file> <output> <width> <height>
videokit --version
Exit codes: 0 success, 1 ffmpeg error, 2 usage error.
MCP tools
| Tool | Purpose |
|---|---|
probe_video | Probe a local video file for duration, dimensions, codecs and format |
get_thumbnail | Extract a single frame of a video as a thumbnail image file |
extract_frames | Extract frames of a video as image files in an output directory at a given rate |
extract_audio | Extract the audio track of a video into an audio file |
trim_video | Trim a video to a segment starting at an offset, optionally with a duration |
transcode_video | Transcode a video to another container format |
resize_video | Resize a video to the given width and height |
MCP client config:
{
"mcpServers": {
"videokit": {
"command": "npx",
"args": ["-y", "@reneturcios/videokit", "mcp"]
}
}
}
Docker
docker run -i ghcr.io/cloudcorprecords/videokit # MCP server (ffmpeg unavailable in-image)
docker run --rm ghcr.io/cloudcorprecords/videokit --version
Development
npm install
npm run build
npm test
MIT license.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.