Skip to main content
Glama
YouTube Transcript MCP Server

YouTube Transcript MCP Server

by emit-ia

YouTube Transcript MCP Server

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

Features

  • Extract transcripts from YouTube videos

  • Channel processing - Get all videos from a YouTube channel

  • Playlist processing - Get all videos from a YouTube playlist

  • Bulk transcripts - Extract transcripts from all channel or playlist 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

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")

youtube_get_channel_videos

Get detailed video information from a YouTube channel.

Parameters:

  • channelUrl (required): YouTube channel URL (supports @username, /c/, /channel/, /user/ formats)

  • maxVideos (optional): Maximum number of videos to retrieve (default: 50, max: 200)

youtube_get_channel_video_urls

Get just the video URLs from a YouTube channel.

Parameters:

  • channelUrl (required): YouTube channel URL

  • maxVideos (optional): Maximum number of video URLs to retrieve (default: 50, max: 200)

youtube_get_channel_transcripts

Extract transcripts from multiple videos in a YouTube channel.

Parameters:

  • channelUrl (required): YouTube channel URL

  • maxVideos (optional): Maximum number of videos to process (default: 10, max: 50)

  • maxConcurrent (optional): Max concurrent transcript requests (default: 3, max: 10)

youtube_get_playlist_info

Get information about a YouTube playlist.

Parameters:

  • playlistUrl (required): YouTube playlist URL (supports playlist?list= and watch?v=...&list= formats)

youtube_get_playlist_videos

Get detailed video information from a YouTube playlist.

Parameters:

  • playlistUrl (required): YouTube playlist URL

  • maxVideos (optional): Maximum number of videos to retrieve (default: 50, max: 200)

youtube_get_playlist_video_urls

Get just the video URLs from a YouTube playlist.

Parameters:

  • playlistUrl (required): YouTube playlist URL

  • maxVideos (optional): Maximum number of video URLs to retrieve (default: 50, max: 200)

youtube_get_playlist_transcripts

Extract transcripts from multiple videos in a YouTube playlist.

Parameters:

  • playlistUrl (required): YouTube playlist URL

  • maxVideos (optional): Maximum number of videos to process (default: 50, max: 200)

  • maxConcurrent (optional): Max concurrent transcript requests (default: 3, max: 10)

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
});

// Get all videos from a channel
const channelVideos = await youtube_get_channel_videos({
  channelUrl: "https://youtube.com/@channelname",
  maxVideos: 25
});

// Get just the video URLs
const videoUrls = await youtube_get_channel_video_urls({
  channelUrl: "https://youtube.com/c/ChannelName",
  maxVideos: 50
});

// Get transcripts from channel videos
const channelTranscripts = await youtube_get_channel_transcripts({
  channelUrl: "https://youtube.com/@channelname",
  maxVideos: 10,
  maxConcurrent: 3
});

// Get playlist information
const playlistInfo = await youtube_get_playlist_info({
  playlistUrl: "https://youtube.com/playlist?list=PLrAXtmRdnEQy6nuLMHjMZOz59Mgq_SUoL"
});

// Get all videos from a playlist
const playlistVideos = await youtube_get_playlist_videos({
  playlistUrl: "https://youtube.com/playlist?list=PLrAXtmRdnEQy6nuLMHjMZOz59Mgq_SUoL",
  maxVideos: 50
});

// Get transcripts from playlist videos
const playlistTranscripts = await youtube_get_playlist_transcripts({
  playlistUrl: "https://youtube.com/playlist?list=PLrAXtmRdnEQy6nuLMHjMZOz59Mgq_SUoL",
  maxVideos: 25,
  maxConcurrent: 3
});

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

Available Tools

11 tools
youtube_batch_transcriptsC

Extract transcripts from multiple YouTube videos

Inputs: urls (required), language, maxConcurrent.

youtube_get_channel_transcriptsC

Get transcripts from multiple videos in a YouTube channel

Inputs: channelUrl (required), maxVideos, maxConcurrent.

youtube_get_channel_videosC

Get video list from a YouTube channel

Inputs: channelUrl (required), maxVideos.

youtube_get_channel_video_urlsC

Get video URLs from a YouTube channel

Inputs: channelUrl (required), maxVideos.

youtube_get_playlist_infoC

Get information about a YouTube playlist

Inputs: playlistUrl (required).

youtube_get_playlist_transcriptsC

Get transcripts from multiple videos in a YouTube playlist

Inputs: playlistUrl (required), maxVideos, maxConcurrent.

youtube_get_playlist_videosC

Get video list from a YouTube playlist

Inputs: playlistUrl (required), maxVideos.

youtube_get_playlist_video_urlsC

Get video URLs from a YouTube playlist

Inputs: playlistUrl (required), maxVideos.

youtube_get_transcriptC

Extract transcript from a YouTube video URL

Inputs: url (required), language, format.

youtube_search_transcriptC

Search for specific text within a YouTube video transcript

Inputs: url (required), query (required), contextWindow, caseSensitive, +1 more.

youtube_transcript_summaryB

Get a formatted summary of transcript content

Inputs: url (required), summaryType, language.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 11 tools

    Disambiguation4/5

    Most tools have distinct purposes targeting different YouTube resources (videos, channels, playlists) and actions (get transcripts, get videos, get URLs, search, summarize). However, youtube_get_channel_videos and youtube_get_channel_video_urls could potentially be confused as both retrieve video information from channels, though one provides lists and the other URLs.

    Naming Consistency5/5

    All tools follow a consistent snake_case naming pattern with a clear youtube_ prefix followed by verb_noun structure (e.g., youtube_get_transcript, youtube_search_transcript, youtube_transcript_summary). The naming convention is predictable and readable throughout the entire set.

    Tool Count4/5

    With 11 tools, the count is reasonable for a YouTube transcript-focused server. It covers multiple aspects of the domain (videos, channels, playlists) but might be slightly heavy with some overlapping functionality (e.g., multiple channel and playlist tools that could potentially be consolidated).

    Completeness5/5

    The tool set provides comprehensive coverage for YouTube transcript operations, including extraction from individual videos, batches, channels, and playlists, plus search and summarization capabilities. There are no obvious gaps for the stated purpose of transcript handling, with good lifecycle coverage from retrieval to analysis.

    Related MCP Connectors