Video Extract runs on your own machine — the client starts it, so there is no endpoint to ping. 495 installs a week from npm. Last commit 23 Sep 2026.
Download any video from a URL, or get its transcript and key frames. All local, no API keys.
What the code does
We read the source, 1 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
spawn(id: number, pid: number, command: string): void;
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add video-extract-mcp -- npx -y @yanlinglabs/video-extract-mcp{
"mcpServers": {
"video-extract-mcp": {
"command": "npx",
"args": [
"-y",
"@yanlinglabs/video-extract-mcp"
]
}
}
}[mcp_servers.video-extract-mcp]
command = "npx"
args = ["-y", "@yanlinglabs/video-extract-mcp"]{
"mcpServers": {
"video-extract-mcp": {
"command": "npx",
"args": [
"-y",
"@yanlinglabs/video-extract-mcp"
]
}
}
}{
"servers": {
"video-extract-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@yanlinglabs/video-extract-mcp"
]
}
}
}Optional settings from the registry entry, left out of the block above:
VIDEO_EXTRACT_COOKIES_FROM_BROWSER (Set to 'auto' to borrow browser cookies only when a platform refuses a download (age-restricted, members-only, or bot-checked media)), VIDEO_EXTRACT_MODELS_DIR (Where local speech models live. Defaults to ~/.cache/video-extract-mcp/models; they are fetched on demand), VIDEO_EXTRACT_MAX_CONCURRENCY (How many analyses may run at once. Default 2; each peaks at about 2 GB when Whisper transcribes, 1.1 GB with SenseVoice).
Alternatives to Video Extract
same job, measured the same wayAnalyze any video (local file or URL) into frames + transcript for Claude Code
Probe, trim, transcode and extract frames or audio from local video files with ffmpeg.
Let an AI watch a video: timestamped transcript, scene-selected keyframes and exact frames. Local.
Make videos AI-readable. Extract timestamped frames and transcripts from any video for AI agents.
Download all images from any web page or extract image URLs, with sizes, formats and alt text.
YouTube transcripts, video search, chapters and extractive summaries. No YouTube API key, no LLM.
Local, offline transcription, speakers, keyframes, on-screen text and review of any audio or video.
Download, transcribe, and get metadata for any video/audio URL. Managed yt-dlp + speech-to-text.
Video Extract — questions
Answers built from our own checks of this server.