Serpapi Youtube MCP Server

🚀 YouTube Data MCP Server

A Model Context Protocol (MCP) server for extracting transcripts and comments from YouTube videos. This server provides tools to obtain YouTube video transcripts and comments for analysis and summarization.

🚀 Quick Start

This MCP server is designed to extract transcripts and comments from YouTube videos. It offers a set of tools to facilitate data retrieval for analysis and summarization.

✨ Features

• getTranscript: Extract subtitles/transcripts from YouTube videos.
• getVideoInfo: Retrieve basic information about YouTube videos.
• getReplies: Fetch comments from YouTube videos (using SerpAPI).
• getCommentReplies: Obtain replies to specific YouTube comments.

📦 Installation

Requirements

• Node.js 16+
• TypeScript
• SerpAPI API key (required for comment functionality)

Steps for Developers

# Clone the repository
git clone https://github.com/diasm3/serpapi-youtube-mcp-server.git
cd youtube-data-mcp

# Install dependencies
npm install

📚 Documentation

Configuration

Create a .env file in the project root directory and add your SerpAPI key:

SERPAPI_KEY=your_serpapi_key_here

You can register at SerpAPI to obtain a SerpAPI key.

Building and Running

# Build the project
npm run build

# Start the server
npm start

The server will start running and listen for commands on stdin/stdout.

Using with Claude

To use this MCP server with Claude:

1. Add the server to your Claude configuration file:

{
  "mcpServers": {
    "youtube-data": {
      "command": "npx",
      "args": ["-y","youtube-data-mcp"],
      "env": {
        "SERPAPI_KEY": "your_serpapi_key_here"
      }
    }
  }
}

2. Restart Claude to apply the configuration.
3. You can now use the following features:
   • getTranscript: Extract transcripts from YouTube videos.
   • getVideoInfo: Retrieve video information.
   • getReplies: Fetch comments.
   • getCommentReplies: Obtain replies.

💻 Usage Examples

API Tools

• youtube_search(query): Search for YouTube videos based on keywords.

  • Parameters:
    • query: The keyword or phrase to search for.
  • Returns:
    • A list of search results containing video IDs and titles.

• get_transcript(video_id): Extract transcripts from a specified YouTube video.

  • Parameters:
    • video_id: The unique identifier of the YouTube video.
  • Returns:
    • Transcript content and metadata.

• get_video_info(video_id): Get detailed information about a YouTube video.

  • Parameters:
    • video_id: The unique identifier of the YouTube video.
  • Returns:
    • Video title, description, publisher information, and statistics (views, likes, etc.).

• get_comments(video_id, page_token): Fetch comments from a YouTube video with pagination support.

  • Parameters:
    • video_id: The unique identifier of the YouTube video.
    • page_token: A pagination token for fetching more comments (optional, default is null).
  • Returns:
    • A list of comments on the current page and a new pagination token.

• get_comment_replies(comment_id, page_token): Obtain all replies to a specific comment with pagination support.

  • Parameters:
    • comment_id: The unique identifier of the specific comment.
    • page_token: A pagination token for fetching more replies (optional, default is null).
  • Returns:
    • A list of replies on the current page and a new pagination token.

🔧 Technical Details

Troubleshooting

• If you encounter a 400 error, check if your SerpAPI key is valid and correctly set in the .env file.
• Review the server logs for detailed error information and debugging data.
• For comment-related issues, ensure that SerpAPI supports the currently used YouTube Video API format.

📄 License

This project is licensed under the MIT license.