The yt-dlp-mcp server implements the Model Context Protocol (MCP) to provide video and audio download capabilities from platforms like YouTube, Facebook, and TikTok for Large Language Models. It enables LLMs to extract video information, download subtitles, search for videos, and more without requiring direct content access.
First, install yt-dlp on your system:
# Windows
winget install yt-dlp
# macOS
brew install yt-dlp
# Linux
pip install yt-dlp
{
"mcpServers": {
"yt-dlp": {
"command": "npx",
"args": [
"-y",
"@kevinwatt/yt-dlp-mcp"
]
}
}
}
If you need to start the server manually:
npx @kevinwatt/yt-dlp-mcp
Use the search_videos tool to find videos on YouTube:
query (search keywords or phrase)maxResults (number between 1-50, defaults to 10)The list_subtitle_languages tool shows all available subtitle languages for a video:
url (video URL)The download_video_subtitles tool fetches subtitles in SRT format:
url (video URL)language (language code like 'en', 'zh-Hant'; defaults to 'en')The download_transcript tool provides a plain text transcript without timestamps:
url (video URL)language (language code; defaults to 'en')The download_video tool saves videos to your Downloads folder:
url (video URL)resolution ('480p', '720p', '1080p', 'best'; defaults to '720p')startTime (format: HH:MM:SS[.ms], e.g., '00:01:30.500')endTime (format: HH:MM:SS[.ms], e.g., '00:02:45.500')The download_audio tool saves audio in the best available quality:
url (video URL)The get_video_metadata tool extracts comprehensive video information:
url (video URL)fields (array of specific metadata fields to extract)The get_video_metadata_summary tool provides a human-readable summary:
url (video URL)You can instruct your LLM with prompts like:
yt-dlp in system PATHTo add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "yt-dlp" '{"command":"npx","args":["-y","@kevinwatt/yt-dlp-mcp"]}'See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:
{
"mcpServers": {
"yt-dlp": {
"command": "npx",
"args": [
"-y",
"@kevinwatt/yt-dlp-mcp"
]
}
}
}To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json~/.config/Claude/claude_desktop_config.json2. Add this to your configuration file:
{
"mcpServers": {
"yt-dlp": {
"command": "npx",
"args": [
"-y",
"@kevinwatt/yt-dlp-mcp"
]
}
}
}3. Restart Claude Desktop for the changes to take effect