YouTube Data

by icraft2170

v1.0.16

MIT

Repository Docs npm

Web & Search

youtubevideotranscriptsresearch

Summary

Search YouTube, read video transcripts, and pull channel statistics from an AI client.

Features

Search videos and retrieve full metadata
Fetch transcripts in multiple languages
Channel statistics and trending video lookup

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

Open your agent's MCP configuration file.
Merge the snippet below into it, filling in the environment variables with your own values.
Restart the agent — the "YouTube Data" tools will be available.

{
  "mcpServers": {
    "youtube-data": {
      "command": "npx",
      "args": [
        "-y",
        "youtube-data-mcp-server"
      ],
      "env": {
        "YOUTUBE_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Code

Add the server with a single CLI command.

claude mcp add youtube-data -e YOUTUBE_API_KEY=your-api-key -- npx -y youtube-data-mcp-server

Claude Desktop

Add the server to claude_desktop_config.json (Settings → Developer → Edit Config).

{
  "mcpServers": {
    "youtube-data": {
      "command": "npx",
      "args": [
        "-y",
        "youtube-data-mcp-server"
      ],
      "env": {
        "YOUTUBE_API_KEY": "your-api-key"
      }
    }
  }
}

Cursor

{
  "command": "npx",
  "args": [
    "-y",
    "youtube-data-mcp-server"
  ],
  "env": {
    "YOUTUBE_API_KEY": "your-api-key"
  }
}

Windsurf

{
  "command": "npx",
  "args": [
    "-y",
    "youtube-data-mcp-server"
  ],
  "env": {
    "YOUTUBE_API_KEY": "your-api-key"
  }
}

VS Code

{
  "command": "npx",
  "args": [
    "-y",
    "youtube-data-mcp-server"
  ],
  "env": {
    "YOUTUBE_API_KEY": "your-api-key"
  }
}

Description

This MCP server connects an assistant to the YouTube Data API, with transcript retrieval as the feature that makes it genuinely useful.

What it provides

Video search with filters for date, duration, and relevance
Video details — title, description, statistics, tags, and publication data
Transcripts in available languages, which is the whole point: a transcript turns an hour-long video into text an assistant can summarise, quote, and answer questions from
Channel information and statistics
Related videos and trending lists by region and category

Where it is genuinely valuable

Research. Conference talks, technical deep-dives, interviews, and tutorials contain a lot of information that exists nowhere in text form. Being able to say "summarise this talk and pull out the part about deployment" is a real capability rather than a novelty.

It is also useful for content analysis — comparing how a topic is covered across channels, or tracking what is performing in a category.

Setup

Requires a YouTube Data API key from Google Cloud. The API has a daily quota, so heavy searching can exhaust it. Runs with npx -y youtube-data-mcp-server.