YouTube Content Extractor

Provides extraction of YouTube video title, description, transcripts, and metadata for downstream processing.

javascript

1

GitHub Stars

javascript

Language

5 months ago

First Indexed

2 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": {
    "custardcream98-youtube-scrap-mcp": {
      "command": "npx",
      "args": [
        "youtube-scrap-mcp"
      ]
    }
  }
}

You can run a dedicated MCP server that extracts YouTube video data, including titles, descriptions, transcripts, and metadata, and exposes it to your MCP client for downstream processing and analysis.

How to use

You run the YouTube Content Extractor MCP as a local process or via an MCP endpoint and connect to it with your MCP client. When you query a YouTube video, the server returns the video title, description, a transcript (from subtitles or Whisper speech-to-text), and video metadata. Use this to automate data collection, indexing, and content analysis for your workflows.

How to install

Prerequisites you need before installing the MCP server are Python and Node tooling, plus the specific dependencies for content extraction and transcription.

Required dependencies you should install first:

# YouTube content extraction
pip install yt-dlp
# or via Homebrew
brew install yt-dlp

# Whisper transcription (fallback)
pip install openai-whisper
# or via Homebrew
brew install openai-whisper

Option 1: NPM Package (Recommended)

Install the MCP server package globally and use the built‑in MCP client wrapper.

npm install -g youtube-scrap-mcp

{
  "mcpServers": {
    "youtube_scrap": {
      "command": "npx",
      "args": ["youtube-scrap-mcp"]
    }
  }
}

Option 2: From Source

If you prefer to build from source, clone the repository, install dependencies, and build before running.

git clone https://github.com/your-username/youtube-scrap-mcp.git
cd youtube-scrap-mcp
pnpm install
pnpm build

{
  "mcpServers": {
    "youtube_scrap": {
      "command": "node",
      "args": ["/path/to/youtube-scrap-mcp/dist/stdio.js"]
    }
  }
}

Notes and troubleshooting

Verify that all prerequisites are installed by checking the versions: yt-dlp --version and whisper --help.
If you install with npm and plan to run the MCP server frequently, consider using the npm or npx options for convenient startup.

Available tools

extractVideoInfo

Fetches YouTube video title, description, and metadata for a given video URL or ID.

extractTranscript

Obtains a transcript from subtitles or uses Whisper transcription as a fallback when subtitles are unavailable.

extractMetadata

Returns additional video metadata such as duration, language, and format details to enrich the data payload.