YouTube Transcript

Provides an MCP server to extract and process YouTube video transcripts, including channel/playlist processing and multi-format outputs.
  • javascript

0

GitHub Stars

javascript

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

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

You can run a specialized MCP server that extracts and processes YouTube video transcripts. It supports single transcripts, channel/playlist bulk processing, multi-format outputs, and context-aware search, all accessible through a consistent MCP interface.

How to use

You connect to this MCP server from your MCP client (for example, a Claude Desktop configuration) and call its tools to extract, search, and organize transcripts from YouTube videos. You can run transcripts for individual videos, gather transcripts from entire channels or playlists, and output results in formats such as JSON, text, SRT, or VTT. Use the channel/playlist helpers to fetch multiple videos and then process them in batches.

Two starting methods are supported. If you prefer a quick start without installing anything locally, you can run the server with NPX. If you want to run the server from your own environment, you can install locally, build, and run the runtime file.

// NPX: run directly without local install
{
  "mcpServers": {
    "youtube-transcript": {
      "command": "npx",
      "args": ["@emit-ia/youtube-transcript-mcp"]
    }
  }
}
// Local installation: after building, run the built runtime via Node
{
  "mcpServers": {
    "youtube-transcript": {
      "command": "node",
      "args": ["/path/to/youtube-transcript-mcp/build/index.js"]
    }
  }
}

How to install

Prerequisites you need before installing: Node.js 18 or newer and Git. You will also use npm to install dependencies and build the project when running locally.

Option A — Run with NPX (no local install required)

npx @emit-ia/youtube-transcript-mcp

Option B — Local installation and build (recommended if you want full control over the runtime)

# Clone the project
git clone https://github.com/emit-ia/youtube-transcript-mcp.git
cd youtube-transcript-mcp

# Install dependencies
npm install

# Build the runtime
npm run build

Configuration and usage notes

Add the MCP server entry to your client configuration to enable access from your MCP client. You have two options depending on whether you want to run remotely via NPX or locally with a built runtime.

NPX configuration (no local install)

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

Local installation configuration (point to built index.js)

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

Available tools and how they work

Use these tools to interact with YouTube transcripts. Each tool accepts its own parameters, enabling you to tailor transcripts, search within them, and manage multi-video workflows.

Available tools

youtube_get_transcript

Extract transcript from a YouTube video. Parameters include url (required), language (optional, default en), and format (optional: json, text, srt, vtt; default json).

youtube_search_transcript

Search within a transcript for specific text. Parameters include url (required), query (required), contextWindow (optional, seconds, default 30), caseSensitive (optional, default false), language (optional, default en).

youtube_batch_transcripts

Process multiple video URLs in parallel. Parameters include urls (required array), language (optional, default en), maxConcurrent (optional, default 3).

youtube_transcript_summary

Get a formatted summary of a transcript with various summary types such as brief, detailed, topics, or timestamps. Parameters include url (required), summaryType (optional, default brief), language (optional, default en).

youtube_get_channel_videos

Retrieve detailed information for videos in a YouTube channel. Parameters include channelUrl (required) and maxVideos (optional, default 50, max 200).

youtube_get_channel_video_urls

Get just the video URLs from a YouTube channel. Parameters include channelUrl (required) and maxVideos (optional, default 50, max 200).

youtube_get_channel_transcripts

Extract transcripts from multiple videos within a channel. Parameters include channelUrl (required), maxVideos (optional, default 10, max 50), maxConcurrent (optional, default 3, max 10).

youtube_get_playlist_info

Fetch information about a YouTube playlist. Parameters include playlistUrl (required).

youtube_get_playlist_videos

Get detailed video information from a YouTube playlist. Parameters include playlistUrl (required) and maxVideos (optional, default 50, max 200).

youtube_get_playlist_video_urls

Get just the video URLs from a YouTube playlist. Parameters include playlistUrl (required) and maxVideos (optional, default 50, max 200).

youtube_get_playlist_transcripts

Extract transcripts from multiple videos in a playlist. Parameters include playlistUrl (required), maxVideos (optional, default 50, max 200), maxConcurrent (optional, default 3, max 10).

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational