Integrate yt-dlp with Claude, Dive, and other MCP-compatible AI systems. Download videos, extract metadata, get transcripts, and more — all through natural language.
yt-dlp-mcp is an MCP project maintained in the kevinwatt/yt-dlp-mcp repository. The maintainer describes its purpose as “Integrate yt-dlp with Claude, Dive, and other MCP-compatible AI systems. Download videos, extract metadata, get transcripts, and more — all through natural language”. Read the project documentation for the complete scope.
The documented npm package is @kevinwatt/yt-dlp-mcp. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
{
"mcpServers": {
"yt-dlp": {
"command": "npx",
"args": [
"-y",
"@kevinwatt/yt-dlp-mcp@latest"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Independent-index web search for assistants — fresh results without the Google API maze.
Manipulates video files using FFmpeg to resize videos and extract audio in various formats.
Analyzes YouTube videos by extracting transcripts, summarizing content, and answering questions using AI.
Retrieves YouTube video URLs from a specified Watch Later playlist within a given timeframe.
Extracts subtitles from YouTube videos using a provided link.
Enables AI assistants to interact with the YouTube API through the Model Context Protocol (MCP).