Download any video from a URL, or get its transcript and key frames. All local, no API keys.
Connect Runs on your machine
claude mcp add video-extract-mcp -e VIDEO_EXTRACT_COOKIES_FROM_BROWSER=<VIDEO_EXTRACT_COOKIES_FROM_BROWSER> -e VIDEO_EXTRACT_MODELS_DIR=<VIDEO_EXTRACT_MODELS_DIR> -e VIDEO_EXTRACT_MAX_CONCURRENCY=<VIDEO_EXTRACT_MAX_CONCURRENCY> -- npx -y @yanlinglabs/[email protected]{
"mcpServers": {
"video-extract-mcp": {
"command": "npx",
"args": [
"-y",
"@yanlinglabs/[email protected]"
],
"env": {
"VIDEO_EXTRACT_COOKIES_FROM_BROWSER": "<VIDEO_EXTRACT_COOKIES_FROM_BROWSER>",
"VIDEO_EXTRACT_MODELS_DIR": "<VIDEO_EXTRACT_MODELS_DIR>",
"VIDEO_EXTRACT_MAX_CONCURRENCY": "<VIDEO_EXTRACT_MAX_CONCURRENCY>"
}
}
}
}{
"mcpServers": {
"video-extract-mcp": {
"command": "npx",
"args": [
"-y",
"@yanlinglabs/[email protected]"
],
"env": {
"VIDEO_EXTRACT_COOKIES_FROM_BROWSER": "<VIDEO_EXTRACT_COOKIES_FROM_BROWSER>",
"VIDEO_EXTRACT_MODELS_DIR": "<VIDEO_EXTRACT_MODELS_DIR>",
"VIDEO_EXTRACT_MAX_CONCURRENCY": "<VIDEO_EXTRACT_MAX_CONCURRENCY>"
}
}
}
}{
"servers": {
"video-extract-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@yanlinglabs/[email protected]"
],
"env": {
"VIDEO_EXTRACT_COOKIES_FROM_BROWSER": "<VIDEO_EXTRACT_COOKIES_FROM_BROWSER>",
"VIDEO_EXTRACT_MODELS_DIR": "<VIDEO_EXTRACT_MODELS_DIR>",
"VIDEO_EXTRACT_MAX_CONCURRENCY": "<VIDEO_EXTRACT_MAX_CONCURRENCY>"
}
}
}
}Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.
Tools
This server runs locally, so its tools are listed by your MCP client once it starts.
Environment variables
| Name | Description |
|---|---|
VIDEO_EXTRACT_COOKIES_FROM_BROWSEROptional | 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_DIROptional | Where local speech models live. Defaults to ~/.cache/video-extract-mcp/models; they are fetched on demand. |
VIDEO_EXTRACT_MAX_CONCURRENCYOptional | How many analyses may run at once. Default 2; each peaks at about 2 GB when Whisper transcribes, 1.1 GB with SenseVoice. |
Details
| Package | @yanlinglabs/[email protected] (NPM, stdio) |
| First published | 23 Sep 2026 |
| Last updated | 23 Sep 2026 |
| Registry name | com.yanlinglabs/video-extract-mcp |
More ai and media servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.