Video Tools MCP

An MCP server that gives Claude the ability to process videos: transcribe with Whisper, cut reels with FFmpeg, and manage video files.

Tools

Prerequisites

• Python 3.10+

• FFmpeg installed and on PATH (or set FFMPEG_PATH env var)

• Claude Desktop or Claude Code

Quick Start

git clone https://github.com/ZZtopBR/video-tools-mcp.git
cd video-tools-mcp
python3 -m venv venv
source venv/bin/activate    # Windows: venv\Scripts\activate
pip install -r requirements.txt

Configuration

Connect to Claude Desktop

{
  "mcpServers": {
    "video-tools": {
      "command": "/path/to/venv/bin/python",
      "args": ["/path/to/video-tools-mcp/src/server.py"],
      "env": {
        "VT_VIDEOS_DIR": "/path/to/your/videos",
        "FFMPEG_PATH": "ffmpeg"
      }
    }
  }
}

Workflow

1. Transcribe — vt_transcribe generates a timestamped .md alongside the video

2. Analyze — Claude reads the transcript, identifies key segments

3. Cut — vt_cut_reel extracts each segment as a separate file

4. Organize — vt_rename applies consistent naming conventions

License

MIT

Built with OpenAI Whisper, FFmpeg, and MCP by Anthropic.