Retrieves detailed information about a YouTube video including title, description, duration, and statistics
Retrieves the transcript/captions for a YouTube video with optional language selection
Searches for YouTube videos based on keywords, filters, and sorting options
Retrieves information about a YouTube channel including statistics and metadata
Lists videos from a specific YouTube channel with pagination support
Retrieves information about a YouTube playlist including title and item count
Lists videos contained within a YouTube playlist with pagination support
Retrieves view count, likes, comments, and other statistics for a YouTube video
The YouTube MCP provides a comprehensive interface for AI language models to interact with YouTube content. It enables access to video information, transcripts, channel details, and playlist management through the YouTube Data API. With this MCP, you can search videos, retrieve transcripts in multiple languages, analyze video statistics, and manage channel content seamlessly.
The YouTube MCP Server provides AI language models with the ability to interact with YouTube content through a standardized interface. This MCP leverages the YouTube Data API to provide comprehensive access to video information, transcripts, channel details, and playlist management.
For Claude Desktop users, the easiest installation method is via Smithery:
npx -y @smithery/cli install @ZubeidHendricks/youtube --client claude
You can install the package directly using npm:
npm install zubeid-youtube-mcp-server
The YouTube MCP Server requires the following environment variables:
YOUTUBE_API_KEY
: Your YouTube Data API key (required)YOUTUBE_TRANSCRIPT_LANG
: Default language for transcripts (optional, defaults to 'en')Add the following to your Claude Desktop configuration:
{
"mcpServers": {
"youtube": {
"command": "npx",
"args": ["-y", "zubeid-youtube-mcp-server"],
"env": {
"YOUTUBE_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}
Add the following to your VS Code settings.json file:
{
"mcp": {
"inputs": [
{
"type": "promptString",
"id": "apiKey",
"description": "YouTube API Key",
"password": true
}
],
"servers": {
"youtube": {
"command": "npx",
"args": ["-y", "zubeid-youtube-mcp-server"],
"env": {
"YOUTUBE_API_KEY": "${input:apiKey}"
}
}
}
}
}
Alternatively, you can create a .vscode/mcp.json
file in your workspace with similar configuration.
Once configured, you can ask your AI assistant to perform various YouTube-related tasks:
If you encounter issues:
Be aware that the YouTube Data API has quota limits. Each API operation consumes quota points, and there's a daily limit. Plan your usage accordingly to avoid hitting these limits.