Package Exports

@emit-ia/youtube-transcript-mcp
@emit-ia/youtube-transcript-mcp/build/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@emit-ia/youtube-transcript-mcp) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

YouTube Transcript MCP Server

An MCP (Model Context Protocol) server for extracting and processing YouTube video transcripts.

Features

Extract transcripts from YouTube videos
Search within transcripts for specific content
Batch processing of multiple videos
Multiple output formats (JSON, text, SRT, VTT)
Context-aware search with configurable windows

Installation

Via NPX (Recommended)

npx @emit-ia/youtube-transcript-mcp

Local Development

git clone https://github.com/emit-ia/youtube-transcript-mcp.git
cd youtube-transcript-mcp
npm install
npm run build

Usage

As MCP Server

Option 1: Via NPX

Add to your Claude Desktop configuration:

{
  "mcpServers": {
    "youtube-transcript": {
      "command": "npx",
      "args": ["@emit-ia/youtube-transcript-mcp"]
    }
  }
}

Option 2: Local Installation

Add to your Claude Desktop configuration:

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

Available Tools

`youtube_get_transcript`

Extract transcript from a YouTube video.

Parameters:

url (required): YouTube video URL
language (optional): Language code (default: "en")
format (optional): Output format - "json", "text", "srt", "vtt" (default: "json")

`youtube_search_transcript`

Search for specific text within a transcript.

Parameters:

url (required): YouTube video URL
query (required): Text to search for
contextWindow (optional): Seconds of context (default: 30)
caseSensitive (optional): Case sensitive search (default: false)
language (optional): Language code (default: "en")

`youtube_batch_transcripts`

Process multiple videos simultaneously.

Parameters:

urls (required): Array of YouTube video URLs
language (optional): Language code (default: "en")
maxConcurrent (optional): Max concurrent requests (default: 3)

`youtube_transcript_summary`

Get formatted summary of transcript content.

Parameters:

url (required): YouTube video URL
summaryType (optional): "brief", "detailed", "topics", "timestamps" (default: "brief")
language (optional): Language code (default: "en")

Example Usage

// Get basic transcript
const transcript = await youtube_get_transcript({
  url: "https://youtube.com/watch?v=dQw4w9WgXcQ",
  format: "json"
});

// Search within transcript
const searchResults = await youtube_search_transcript({
  url: "https://youtube.com/watch?v=dQw4w9WgXcQ",
  query: "important topic",
  contextWindow: 30
});

Requirements

Node.js 18+
No API keys required (uses public transcript data)

Limitations

Only works with videos that have public transcripts
Rate limiting may apply for high-volume usage
Transcript availability depends on YouTube's availability

License

MIT