YouTube MCP Server

A Model Context Protocol (MCP) server implementation utilizing the YouTube Data API. It allows AI language models to interact with YouTube content through a standardized interface.

Key Features

Video Information

• Retrieve detailed video information (title, description, duration, statistics)
• Search for videos by keywords
• Get related videos based on a specific video
• Calculate and analyze video engagement ratios

Transcript/Caption Management

• Retrieve video captions with multi-language support
• Specify language preferences for transcripts
• Access time-stamped captions for precise content reference

Channel Analysis

• View detailed channel statistics (subscribers, views, video count)
• Get top-performing videos from a channel
• Analyze channel growth and engagement metrics

Playlist Management

• Retrieve detailed playlist information
• Get all videos within a playlist
• Search for public playlists by keywords
• Get all public playlists from a specific channel

Trend Analysis

• View trending videos by region and category
• Compare performance metrics across multiple videos
• Discover popular content in specific categories

OAuth Authentication for Private Content

This MCP server supports OAuth authentication to access private YouTube content including your personal playlists. To set up and use OAuth:

1. Create OAuth Credentials:

   • Go to the Google Cloud Console
   • Create OAuth 2.0 Client ID credentials (Web application type)
   • Set the authorized redirect URI to http://localhost:3000/oauth2callback
   • Add the client ID and secret to your .env file

2. Authenticate:

   # Start the OAuth flow
   npm run auth
   # This will display a URL to visit in your browser
   

3. Verify Authentication Status:

   npm run auth:status
   

4. Revoke Authentication:

   npm run auth:revoke
   

Once authenticated, you can access your private playlists using the getMyPlaylists tool.

Available Tools

The server provides the following MCP tools:

Installation

Automatic Installation via Smithery

Automatically install YouTube MCP Server for Claude Desktop via Smithery:

npx -y @smithery/cli install @icraft2170/youtube-data-mcp-server --client claude

Manual Installation

# Install from npm
npm install youtube-data-mcp-server

# Or clone repository
git clone https://github.com/icraft2170/youtube-data-mcp-server.git
cd youtube-data-mcp-server
npm install

Environment Configuration

Set the following environment variables:

• YOUTUBE_API_KEY: YouTube Data API key (required)
• YOUTUBE_TRANSCRIPT_LANG: Default caption language (optional, default: 'en')

OAuth Configuration (for Private Playlists)

To access private playlists and content, you'll need to configure OAuth:

• GOOGLE_OAUTH_CLIENT_ID: OAuth 2.0 client ID
• GOOGLE_OAUTH_CLIENT_SECRET: OAuth 2.0 client secret
• OAUTH_REDIRECT_URI: OAuth callback URL (default: http://localhost:3000/oauth2callback)

MCP Client Configuration

Add the following to your Claude Desktop configuration file:

{
  "mcpServers": {
    "youtube": {
      "command": "npx",
      "args": ["-y", "youtube-data-mcp-server"],
      "env": {
        "YOUTUBE_API_KEY": "YOUR_API_KEY_HERE",
        "YOUTUBE_TRANSCRIPT_LANG": "ko"
      }
    }
  }
}

YouTube API Setup

1. Access Google Cloud Console
2. Create a new project or select an existing one
3. Enable YouTube Data API v3
4. Create API credentials (API key)
5. Use the generated API key in your environment configuration

Development

# Install dependencies
npm install

# Run in development mode
npm run dev

# Build
npm run build

Network Configuration

The server exposes the following ports for communication:

• HTTP: 3000
• gRPC: 3001

System Requirements

• Node.js 18.0.0 or higher

Security Considerations

• Always keep your API key secure and never commit it to version control systems
• Manage your API key through environment variables or configuration files
• Set usage limits for your API key to prevent unauthorized use

License

This project is licensed under the MIT License. See the LICENSE file for details.