YouTube

YouTube MCP Server

A Model Context Protocol (MCP) server implementation for YouTube, enabling AI language models to interact with YouTube content through a standardized interface.

Features

Video Information

• Get video details (title, description, duration, etc.)
• List channel videos
• Get video statistics (views, likes, comments)
• Search videos across YouTube

Transcript Management

• Retrieve video transcripts
• Support for multiple languages
• Get timestamped captions
• Search within transcripts

Channel Management

• Get channel details
• List channel playlists
• Get channel statistics
• Search within channel content

Playlist Management

• List playlist items
• Get playlist details
• Search within playlists
• Get playlist video transcripts

Installation

Installing via Smithery

To install YouTube MCP Server for Claude Desktop automatically via Smithery:

1npx -y @smithery/cli install @ZubeidHendricks/youtube --client claude

Manual Installation

1npm install @modelcontextprotocol/server-youtube

Configuration

Set the following environment variables:

• YOUTUBE_API_KEY: Your YouTube Data API key
• YOUTUBE_TRANSCRIPT_LANG: Default language for transcripts (optional, defaults to 'en')

Using with MCP Client

Add this to your MCP client configuration (e.g. Claude Desktop):

1{
2  "mcpServers": {
3    "youtube": {
4      "command": "npx",
5      "args": ["-y", "@modelcontextprotocol/server-youtube"],
6      "env": {
7        "YOUTUBE_API_KEY": "<YOUR_API_KEY>"
8      }
9    }
10  }
11}

YouTube API Setup

1. Go to Google Cloud Console
2. Create a new project or select an existing one
3. Enable the YouTube Data API v3
4. Create API credentials (API key)
5. Copy the API key for configuration

Examples

Managing Videos

1// Get video details
2const video = await youtube.videos.getVideo({
3  videoId: "video-id"
4});
5
6// Get video transcript
7const transcript = await youtube.transcripts.getTranscript({
8  videoId: "video-id",
9  language: "en"
10});
11
12// Search videos
13const searchResults = await youtube.videos.searchVideos({
14  query: "search term",
15  maxResults: 10
16});

Managing Channels

1// Get channel details
2const channel = await youtube.channels.getChannel({
3  channelId: "channel-id"
4});
5
6// List channel videos
7const videos = await youtube.channels.listVideos({
8  channelId: "channel-id",
9  maxResults: 50
10});

Managing Playlists

1// Get playlist items
2const playlistItems = await youtube.playlists.getPlaylistItems({
3  playlistId: "playlist-id",
4  maxResults: 50
5});
6
7// Get playlist details
8const playlist = await youtube.playlists.getPlaylist({
9  playlistId: "playlist-id"
10});

Development

1# Install dependencies
2npm install
3
4# Run tests
5npm test
6
7# Build
8npm run build
9
10# Lint
11npm run lint

Contributing

See CONTRIBUTING.md for information about contributing to this repository.

License

This project is licensed under the MIT License - see the LICENSE file for details.# YouTube MCP Server

A YouTube API integration using the Model Context Protocol.

Setup

1. Clone the repository
2. Install dependencies:

   1npm install

3. Copy .env.example to .env:

   1cp .env.example .env

4. Edit .env and add your YouTube API key
5. Start the server:

   1npm start

Environment Variables

• YOUTUBE_API_KEY: Your YouTube Data API v3 key (get it from Google Cloud Console)

Development

1. To run in development mode with auto-reload:

   1npm run dev

2. To build:

   1npm run build

Security Note

Always keep your API keys secure and never commit them to version control.