yt-dlp
Download video and audio from YouTube and other platforms using the yt-dlp tool.
yt-dlp-mcp
An MCP server implementation that integrates with yt-dlp, providing video and audio content download capabilities from YouTube and other platforms for LLMs.
Features
- Video Download: Save videos to your specified folder with quality control
- Audio Download: Extract and save audio in various formats (mp3, m4a, ogg, opus)
- Video Information: Get metadata about videos without downloading
- Privacy-Focused: Direct download without tracking
- MCP Integration: Works with Claude Desktop and other MCP-compatible LLMs
- Flexible Output: Customizable output paths and file formats
Installation
Prerequisites
Install yt-dlp based on your operating system:
# macOS
brew install yt-dlp
# Linux
pip install yt-dlp
With Claude Desktop
-
Open your Claude Desktop configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- macOS:
-
Add the MCP server configuration:
{
"mcpServers": {
"yt-dlp-mcp": {
"command": "npx",
"args": [
"-y",
"@gtvar/yt-dlp-mcp"
]
}
}
}
- Save the file and restart Claude Desktop
Tool Documentation
-
get_video_info
- Get video metadata without downloading (title, duration, uploader, available formats)
- Inputs:
url(string, required): URL of the video
-
download_video
- Download video or extract audio to specified location with quality control
- Inputs:
url(string, required): URL of the videoquality_preference(string, optional): Video quality preferencevideo_container_preference(string, optional): Preferred video formataudio_container_preference(string, optional): Preferred audio format (mp3, m4a, ogg, opus)output_path(string, optional): Custom output path with filename templateextract_audio_only(boolean, optional): Extract audio only. Defaults to false
Usage Examples
Ask your LLM to:
"Get information about this video: https://youtube.com/watch?v=..."
"Download this YouTube video: https://youtube.com/watch?v=..."
"Extract audio from this video in mp3 format: https://youtube.com/watch?v=..."
"Download video with custom quality settings: https://youtube.com/watch?v=..."
"Save this video to a specific folder: https://youtube.com/watch?v=..."
Manual Start
If needed, start the server manually:
npx @gtvar/yt-dlp-mcp
Environment Variables
YTDLP_PATH- Path to yt-dlp executable (default: 'yt-dlp')YTDL_OUTPUT_DIR- Default output directory (default: '/tmp')FFMPEG_PATH- Path to ffmpeg executable (optional)
Requirements
- Node.js 20+
yt-dlpin system PATH- MCP-compatible LLM service (Claude Desktop, etc.)
- Optional:
ffmpegfor additional format support
License
MIT
Author
gtvar
Related Servers
Bright Data
sponsorDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
Anysite
Turn any website into an API
Markdown Downloader
Download webpages as markdown files using the r.jina.ai service, with configurable directories and persistent settings.
AI Shopping Assistant
A conversational AI shopping assistant for web-based product discovery and decision-making.
XPath MCP Server
Execute XPath queries on XML content.
Xiaohongshu Search & Comment
An automated tool to search notes, retrieve content, and post comments on Xiaohongshu (RedBook) using Playwright.
MCP360
MCP360 is a unified gateway and marketplace that provides 100+ external tools and custom MCPs through a single integration for AI agents.
Scrapfly
Scrapfly MCP Server gives AI agents a simple, unified way to scrape live web data with built-in anti-bot handling.
anybrowse
Convert any URL to LLM-ready Markdown via real Chrome browsers. 3 tools: scrape, crawl, search. Free via MCP, pay-per-use via x402.
Career Site Jobs
A MCP server to retrieve up-to-date jobs from company career sites.
Playwright MCP
Browser automation using Playwright, enabling LLMs to interact with web pages through structured accessibility snapshots.