MCP Video

v1.4.0โ€ขDeveloper Toolsโ€ขstable

๐Ÿ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - Video editing MCP server with 26 tools for trimming, merging, text

agent-toolsai-agentsai-videoclaudeclaude-code
Share:
22
Stars
0
Downloads
0
Weekly
0/5

What is MCP Video?

MCP Video is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ๐Ÿ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - video editing mcp server with 26 tools for trimming, merging, text

๐Ÿ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - Video editing MCP server with 26 tools for trimming, merging, text

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP protocol support

Use Cases

Trim, merge, and edit videos using 26 tools powered by FFmpeg.
Add text overlays and manipulate video content through natural language.
KyaniteLabs

Maintainer

LicenseApache 2.0
Languagepython
Versionv1.4.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

PIP

pip install mcp-video

Manual Installation

pip install mcp-video

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MCP Video

MCP Video is a Python-based MCP server powered by FFmpeg that gives AI assistants a comprehensive video and audio editing toolkit with over 100 tools covering core editing, cinematic creation, AI-assisted media processing, visual effects, transitions, layout and motion, and procedural audio. It integrates with Hyperframes for frame-level video composition and supports optional AI extras including transcription, scene detection, image upscaling, and stem separation. You install it from PyPI and connect it to Claude Code, Claude Desktop, or Cursor to edit video files through natural language.

Prerequisites

  • Python 3.10+ with pip or uv package manager
  • FFmpeg installed and available on PATH (brew install ffmpeg on macOS, apt install ffmpeg on Ubuntu)
  • Node.js 22+ if using Hyperframes integration
  • An MCP-compatible client: Claude Code, Claude Desktop, or Cursor
  • Optional: additional disk space (1โ€“4 GB) for AI extras like transcription or upscaling
1

Install FFmpeg

FFmpeg must be installed and accessible on your PATH before installing mcp-video. Install it using your system package manager.

# macOS
brew install ffmpeg

# Ubuntu/Debian
sudo apt install ffmpeg
2

Install mcp-video from PyPI

Install the core package. Optionally add AI extras for transcription, upscaling, stem separation, or procedural audio. Run the doctor command to verify the installation.

# Core install
pip install mcp-video

# With transcription support (~1 GB)
pip install "mcp-video[transcribe]"

# All AI features
pip install "mcp-video[ai]"

# Verify installation
mcp-video doctor
3

Add mcp-video to Claude Code

Use the Claude CLI to register mcp-video as an MCP server. This uses uvx for isolated execution.

claude mcp add mcp-video -- uvx --from mcp-video mcp-video
4

Configure Claude Desktop or Cursor

Add the server block to your claude_desktop_config.json or Cursor MCP settings file. The server runs via uvx with no additional env vars required for basic use.

{
  "mcpServers": {
    "mcp-video": {
      "command": "uvx",
      "args": ["--from", "mcp-video", "mcp-video"]
    }
  }
}
5

Set Hyperframes path if needed

If Node.js 22+ is installed but the Hyperframes CLI is not auto-detected, set the MCP_VIDEO_HYPERFRAMES_COMMAND environment variable in your config.

{
  "mcpServers": {
    "mcp-video": {
      "command": "uvx",
      "args": ["--from", "mcp-video", "mcp-video"],
      "env": {
        "MCP_VIDEO_HYPERFRAMES_COMMAND": "/usr/local/bin/hyperframes"
      }
    }
  }
}

MCP Video Examples

Client configuration

Standard Claude Desktop configuration for mcp-video using uvx for isolated package execution.

{
  "mcpServers": {
    "mcp-video": {
      "command": "uvx",
      "args": ["--from", "mcp-video", "mcp-video"]
    }
  }
}

Prompts to try

Use these prompts to edit, analyze, and transform video files through your connected MCP client.

- "Trim interview.mp4 from 2:15 to 3:00 and save as clip.mp4"
- "Merge intro.mp4, main.mp4, and outro.mp4 into final.mp4"
- "Transcribe the audio from this video and output an SRT caption file"
- "Detect scene changes in footage.mp4"
- "Add a glitch transition between clip1.mp4 and clip2.mp4"
- "Repurpose this video for YouTube Shorts, Instagram Reel, and TikTok"
- "Add a vignette effect to video.mp4"

Troubleshooting MCP Video

mcp-video doctor reports FFmpeg not found

Ensure ffmpeg is installed and the binary is on your PATH. Run 'which ffmpeg' (macOS/Linux) or 'where ffmpeg' (Windows) to confirm. If using a virtual environment, activate it before installing mcp-video.

AI features like transcription fail to load

Install the relevant extra: 'pip install "mcp-video[transcribe]"' for transcription. These extras require significant disk space (up to 2 GB) and may take time to download model weights on first use.

Hyperframes tools are missing or unavailable

Install Node.js 22+ and ensure the Hyperframes CLI is resolvable. If auto-detection fails, set MCP_VIDEO_HYPERFRAMES_COMMAND to the full path of the Hyperframes binary in your MCP server env config.

Frequently Asked Questions about MCP Video

What is MCP Video?

MCP Video is a Model Context Protocol (MCP) server that ๐Ÿ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - video editing mcp server with 26 tools for trimming, merging, text It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MCP Video?

Install via pip with: pip install mcp-video. Then configure your AI client to connect to this MCP server.

Which AI clients work with MCP Video?

MCP Video works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MCP Video free to use?

Yes, MCP Video is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "pastorsimon1798-mcp-video": { "command": "pip", "args": ["install", "mcp-video"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide โ†’

Ready to use MCP Video?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides