YT Description

Provides a YouTube transcript extraction MCP server for AI assistants to analyze public video captions.

typescript

3

GitHub Stars

typescript

Language

6 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": {
    "malikelate-yt-description-mcp": {
      "command": "node",
      "args": [
        "/absolute/path/to/yt-mcp/build/index.js"
      ]
    }
  }
}

You can use this MCP server to extract transcripts from public YouTube videos, enabling AI assistants to analyze video content directly. It provides a simple, reliable way to fetch captions and use them in downstream workflows or creative applications.

How to use

You integrate the YouTube Transcript MCP with an MCP client so your AI can request transcripts for any public YouTube URL. Provide the video URL, and the server returns the transcript data it can access. Use this to feed video content into analysis, summaries, or prompt-based workflows.

How to install

Prerequisites include Node.js version 16 or higher and a package manager. You will also need access to a YouTube video URL to test transcripts.

Step 1: Clone the project and navigate into the directory.

git clone https://github.com/malikelate/yt-description-mcp.git
cd yt-description-mcp

Step 2: Install dependencies using your preferred package manager.

pnpm install

or

npm install

Step 3: Build the project to produce the runtime artifacts.

pnpm run build

Additional configuration and usage notes

Configure the MCP client to point at the local YouTube Transcript MCP server. You will use a stdio-based command to run the server so the client can invoke it directly.

Configuration

Cursor configuration shows how to register a new MCP server that runs the Node.js build output as a command. Use these steps to configure Cursor and Claude Desktop to access the YouTube Transcript MCP.

1) Open Cursor Settings
2) Navigate to MCP → Add new MCP server
3) Configure with these settings:
   - Name: `youtube_transcript`
   - Type: `stdio`
   - Command: `node`
   - Args: [`/absolute/path/to/yt-mcp/build/index.js`]

Claude Desktop configuration

Add a configuration block so Claude Desktop can start the MCP server locally.

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

Available tools

extractTranscript

Fetch transcripts from a public YouTube video by supplying the video URL; returns the transcript text for downstream processing.