video-editor-mcp

An MCP (Model Context Protocol) server that gives Claude a full conversational video-editing toolkit — trim, crop, color grade, caption, beat-sync, stabilize, and more — built on ffmpeg, faster-whisper, and yt-dlp, with optional DaVinci Resolve and CapCut integration.

Describe the edit you want in chat; Claude calls the tools to do it.

Tools

Related MCP server: Video MCP

Setup

1. Clone and install Python deps

git clone https://github.com/dr-ashraf-s-MCP-LABS/video-editor-mcp.git
cd video-editor-mcp
pip install -r requirements.txt

You'll also need ffmpeg on your PATH (or imageio-ffmpeg, which the server falls back to automatically) and yt-dlp.

2. Configure (optional)

Copy .env.example to .env and adjust if you need non-default binary locations, want to point at your own CapCut/DaVinci install, or need a cookies.txt for Instagram/Facebook downloads (export one with a browser extension like "Get cookies.txt LOCALLY").

3. Register with Claude

Add to your Claude Desktop / Claude Code MCP config:

{
  "mcpServers": {
    "video-editor": {
      "command": "python",
      "args": ["/absolute/path/to/video-editor-mcp/server.py"]
    }
  }
}

Restart Claude and start editing conversationally, e.g.: "Download this reel, match its style to my raw footage, add this music, and caption it."

Notes

• download_video, output, and downloaded files land in ./downloads and ./output next to server.py by default — override with VIDEO_EDITOR_DOWNLOADS_DIR / VIDEO_EDITOR_OUTPUT_DIR.

• CapCut and DaVinci Resolve tools degrade gracefully (report "not installed") if you haven't set the relevant env vars or don't have those apps.

• auto_captions and batch_process's captions mode download the Whisper base model (~150MB) on first use.

License

MIT — see LICENSE.