MCP YouTube Transcript Server

A Model Context Protocol server that enables retrieval of transcripts from YouTube videos. This server provides direct access to video transcripts through a simple interface, making it ideal for content analysis and processing.

Features
Getting Started
- Prerequisites
- Installation
Usage
- Basic Configuration
- Testing
- Troubleshooting and Maintenance
API Reference
Development
Contributing
License

Features

✨ Key capabilities:

Extract transcripts from YouTube videos
Support for multiple languages
Format text with continuous or paragraph mode
Retrieve video titles and metadata
Automatic paragraph segmentation
Text normalization and HTML entity decoding
Robust error handling
Timestamp and overlap detection

Getting Started

Prerequisites

Node.js 18 or higher

Installation

We provide two installation methods:

Option 1: Manual Configuration (Recommended for Production)

Create or edit the Claude Desktop configuration file:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
Add the following configuration:

{
  "mcpServers": {
    "youtube-transcript": {
      "command": "npx",
      "args": [
        "-y",
        "@sinco-lab/mcp-youtube-transcript"
      ]
    }
  }
}

Quick setup script for macOS:

# Create directory if it doesn't exist
mkdir -p ~/Library/Application\ Support/Claude

# Create or update config file
cat > ~/Library/Application\ Support/Claude/claude_desktop_config.json << 'EOL'
{
  "mcpServers": {
    "youtube-transcript": {
      "command": "npx",
      "args": [
        "-y",
        "@sinco-lab/mcp-youtube-transcript"
      ]
    }
  }
}
EOL

Option 2: Via Smithery (Development Only)

npx -y @smithery/cli install @sinco-lab/mcp-youtube-transcript --client claude

⚠️ Note: This method is not recommended for production use as it relies on Smithery's proxy services.

Usage

Basic Configuration

To use with Claude Desktop / Cursor / cline, ensure your configuration matches:

{
  "mcpServers": {
    "youtube-transcript": {
      "command": "npx",
      "args": ["-y", "@sinco-lab/mcp-youtube-transcript"]
    }
  }
}

Testing

With Claude App

Restart the Claude app after installation

Test with a simple command:

https://www.youtube.com/watch?v=AJpK3YTTKZ4 Summarize this video

Example output: Demo

With MCP Inspector

# Clone and setup
git clone https://github.com/sinco-lab/mcp-youtube-transcript.git
cd mcp-youtube-transcript
npm install
npm run build

# Launch inspector
npx @modelcontextprotocol/inspector node "dist/index.js"

# Access http://localhost:5173 and try these commands:
# 1. List Tools: clink `List Tools`
# 2. Test get_transcripts with:
#    url: "https://www.youtube.com/watch?v=AJpK3YTTKZ4"
#    lang: "en" (optional)
#    enableParagraphs: false (optional)

Troubleshooting and Maintenance

Checking Claude Logs

To monitor Claude's logs, you can use the following command:

tail -n 20 -f ~/Library/Logs/Claude/mcp*.log

This will display the last 20 lines of the log file and continue to show new entries as they are added.

Note: Claude app automatically prefixes MCP server log files with mcp-server-. For example, our server's logs will be written to mcp-server-youtube-transcript.log.

Cleaning the `npx` Cache

If you encounter issues related to the npx cache, you can manually clean it using:

rm -rf ~/.npm/_npx

This will remove the cached packages and allow you to start fresh.

API Reference

get_transcripts

Fetches transcripts from YouTube videos.

Parameters:

url (string, required): YouTube video URL or ID
lang (string, optional): Language code (default: "en")
enableParagraphs (boolean, optional): Enable paragraph mode (default: false)

Response Format:

{
  "content": [{
    "type": "text",
    "text": "Video title and transcript content",
    "metadata": {
      "videoId": "video_id",
      "title": "video_title",
      "language": "transcript_language",
      "timestamp": "processing_time",
      "charCount": "character_count",
      "transcriptCount": "number_of_transcripts",
      "totalDuration": "total_duration",
      "paragraphsEnabled": "paragraph_mode_status"
    }
  }]
}

Development

Project Structure

├── src/
│ ├── index.ts            # Server entry point
│ ├── youtube.ts          # YouTube transcript fetching logic
├── dist/                 # Compiled output
└── package.json

Key Components

YouTubeTranscriptFetcher: Core transcript fetching functionality
YouTubeUtils: Text processing and utilities

Features and Capabilities

Error Handling:
- Invalid URLs/IDs
- Unavailable transcripts
- Language availability
- Network errors
- Rate limiting
Text Processing:
- HTML entity decoding
- Punctuation normalization
- Space normalization
- Smart paragraph detection

Contributing

We welcome contributions! Please feel free to submit issues and pull requests.

License

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

MCP YouTube Transcript Server