Kinocut

Name: Kinocut
Author: KyaniteLabs

by KyaniteLabscommunityv1.7.0

Kinocut is an MCP server, Python library, and CLI for AI agents to perform guardrailed video editing on local media using FFmpeg. It supports tasks like trimming, resizing, subtitles, audio, effects, workflow planning/validation/rendering, and quality checks with provenance receipts.

From the registry: Guardrailed video editing for AI agents: FFmpeg, captions, effects, Hyperframes, and receipts.

GitHub Repository Website

Install & configure

Prerequisites

required
Install FFmpeg
FFmpeg must be installed and available on PATH.
```
$ brew install ffmpeg
```
https://ffmpeg.org/
required
Install FFmpeg
FFmpeg must be installed and available on PATH.
```
$ sudo apt install ffmpeg
```
https://ffmpeg.org/
required
Install uv
The recommended portable launch method uses uvx, which requires uv to be installed.
https://docs.astral.sh/uv/
optional
Optional: install Python package extras
Optional Kinocut features require installing package extras such as transcribe, image, stems, upscale, audio, or ai.
```
$ pip install "kinocut[transcribe,image,stems,upscale,audio,ai]"
```
https://pypi.org/project/kinocut/
optional
Optional: install Node.js and Hyperframes CLI
Hyperframes tools additionally require Node.js 22+ and a resolvable hyperframes CLI on PATH, unless MCP_VIDEO_HYPERFRAMES_COMMAND is set.
https://hyperframes.io/

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `kinocut` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install FFmpeg** — FFmpeg must be installed and available on PATH. Run: `brew install ffmpeg` (https://ffmpeg.org/)
- **Install FFmpeg** — FFmpeg must be installed and available on PATH. Run: `sudo apt install ffmpeg` (https://ffmpeg.org/)
- **Install uv** — The recommended portable launch method uses uvx, which requires uv to be installed. (https://docs.astral.sh/uv/)

Optional prerequisites:
- Optional: install Python package extras — Optional Kinocut features require installing package extras such as transcribe, image, stems, upscale, audio, or ai. Run: `pip install "kinocut[transcribe,image,stems,upscale,audio,ai]"` (https://pypi.org/project/kinocut/)
- Optional: install Node.js and Hyperframes CLI — Hyperframes tools additionally require Node.js 22+ and a resolvable hyperframes CLI on PATH, unless MCP_VIDEO_HYPERFRAMES_COMMAND is set. (https://hyperframes.io/)

Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["--from","kinocut","kino"]
- optional environment variables:
  - `MCP_VIDEO_HYPERFRAMES_COMMAND`: Command path/name to use for the Hyperframes CLI if it is not otherwise resolvable on PATH. (example: `<your-hyperframes-command>`)

Note: Recommended MCP launch uses uvx with the kinocut package. No environment variables are required for the core FFmpeg editing tools. Optional features depend on installed package extras and local runtimes. Hyperframes-related tools need Node.js 22+ plus a resolvable Hyperframes CLI.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: Recommended MCP launch uses uvx with the kinocut package. No environment variables are required for the core FFmpeg editing tools. Optional features depend on installed package extras and local runtimes. Hyperframes-related tools need Node.js 22+ plus a resolvable Hyperframes CLI.