Mcp Video

Name: Mcp Video
Author: KyaniteLabs

by KyaniteLabscommunityv1.3.10

113

mcp-video is an MCP server, Python library, and CLI that exposes structured video-editing tools for AI agents. It wraps FFmpeg and related workflows for trimming, resizing, subtitles, audio, effects, media analysis, quality checks, and repurposing clips into platform-ready outputs.

From the registry: Video editing MCP server with 91 FFmpeg, planning, and Hyperframes tools.

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 to run the server without a global install.
https://docs.astral.sh/uv/
optional
Install Node.js 22+
Required only if you plan to use Hyperframes tools, which call the Hyperframes CLI through npx.

Install in your client

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

Please install the `mcp-video` 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 to run the server without a global install. (https://docs.astral.sh/uv/)

Optional prerequisites:
- Install Node.js 22+ — Required only if you plan to use Hyperframes tools, which call the Hyperframes CLI through npx.

Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["--from","mcp-video","mcp-video"]

Note: README also shows an alternative pip install path, but the simplest portable MCP launch is via uvx. No MCP-specific environment variables are documented.

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: README also shows an alternative pip install path, but the simplest portable MCP launch is via uvx. No MCP-specific environment variables are documented.