YouTube Transcript Extractor MCP

by MalikElate
Verified

local-only server

The server can only run on the client’s local machine because it depends on local resources.

Integrations

  • Enables extraction of transcripts from any public YouTube video, allowing AI assistants to analyze and work with YouTube video content directly.

YouTube Transcript Extractor MCP πŸŽ₯

A Model Context Protocol (MCP) server that enables AI assistants to extract transcripts from YouTube videos. Built for integration with Cursor and Claude Desktop, this tool allows AI to analyze and work with YouTube video content directly.

Features

  • 🎯 Extract transcripts from any public YouTube video
  • πŸ”Œ Easy integration with Cursor and Claude Desktop
  • πŸš€ Built with TypeScript for type safety
  • πŸ“¦ Simple setup and deployment
  • πŸ› οΈ Based on the Model Context Protocol

Prerequisites

  • Node.js (v16 or higher)
  • pnpm (recommended) or npm
  • A YouTube video URL to extract transcripts from

Installation

  1. Clone the repository:
git clone https://github.com/yourusername/yt-mcp.git cd yt-mcp
  1. Install dependencies:
pnpm install
  1. Build the project:
pnpm run build

Configuration

For Cursor

  1. Open Cursor Settings
  2. Navigate to MCP β†’ Add new MCP server
  3. Configure with these settings:
    • Name: youtube-transcript
    • Type: command
    • Command: node /absolute/path/to/yt-mcp/build/index.js

For Claude Desktop

Add this configuration to your Claude Desktop config:

{ "mcpServers": { "youtube-transcript": { "command": "node", "args": ["/absolute/path/to/yt-mcp/build/index.js"] } } }

Usage

Once configured, the AI can extract transcripts from YouTube videos by calling the tool with a video URL. Example:

// The AI will use this format internally const transcript = await extractTranscript({ input: "https://www.youtube.com/watch?v=VIDEO_ID" });

Technical Details

The server is built using:

Limitations

  • Only works with public YouTube videos
  • Videos must have captions/subtitles enabled
  • Some videos may have auto-generated captions which might not be 100% accurate

Troubleshooting

Common issues and solutions:

  1. "Cannot find video ID" error
    • Ensure the YouTube URL is complete and correct
    • Check if the video is publicly accessible
  2. "No transcript available" error
    • Verify that the video has captions enabled
    • Try a different video to confirm the tool is working
  3. Build errors
    • Make sure all dependencies are installed
    • Check Node.js version (should be v16 or higher)

Contributing

Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.

License

MIT

-
security - not tested
F
license - not found
-
quality - not tested

A Model Context Protocol server that enables AI assistants to extract transcripts from YouTube videos, allowing AI to analyze and work with video content directly.

  1. Features
    1. Prerequisites
      1. Installation
        1. Configuration
          1. For Cursor
          2. For Claude Desktop
        2. Usage
          1. Technical Details
            1. Limitations
              1. Troubleshooting
                1. Contributing
                  1. License