YouTube

v0.2.6Search & Data Extractionstable

Get detailed information about multiple YouTube videos. Returns comprehensive data including video metadata, statistics, and content details. Use this when you need complete information about specific

mcpmodel-context-protocolyoutubeyoutube-apiclaude
Share:
48
Stars
0
Downloads
0
Weekly
0/5

What is YouTube?

YouTube is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to get detailed information about multiple youtube videos. returns comprehensive data including video metadata, statistics, and content details. use this when you need complete information about specific

Get detailed information about multiple YouTube videos. Returns comprehensive data including video metadata, statistics, and content details. Use this when you need complete information about specific

This server falls under the Search & Data Extraction category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • download_youtube_url

Use Cases

Get detailed video metadata and statistics
Search YouTube content
kirbah

Maintainer

LicenseMIT License
Languagepython
Versionv0.2.6
UpdatedMar 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y @kirbah/mcp-youtube

Manual Installation

npx -y @kirbah/mcp-youtube

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use YouTube

The mcp-youtube server gives AI assistants rich access to YouTube data via the YouTube Data API v3, exposing tools for fetching video metadata and statistics, extracting transcripts and captions, searching YouTube content, retrieving channel statistics and top videos, discovering trending videos by region and category, and reading video comments. It works in a zero-config transcript-only mode without an API key, and unlocks the full suite of tools when a YouTube Data API key is provided. An optional MongoDB connection string enables caching to reduce API quota consumption.

Prerequisites

  • Node.js 20.0.0 or higher installed
  • A YouTube Data API v3 key from Google Cloud Console (required for search, statistics, and most tools; not needed for transcript-only mode)
  • Optional: A MongoDB Atlas connection string for response caching to reduce API quota usage
  • An MCP client such as Claude Desktop or Cursor
1

Obtain a YouTube Data API v3 key

Go to console.cloud.google.com, create or select a project, enable the YouTube Data API v3, and create an API key under Credentials. Copy the key for the next step.

2

Test the server with npx (no install required)

Run the server directly with npx to confirm it works before adding it to your client config. In transcript-only mode no API key is needed.

npx -y @kirbah/mcp-youtube
3

Configure Claude Desktop with your API key

Add the server entry to claude_desktop_config.json, providing your YOUTUBE_API_KEY to unlock all tools. Optionally add MDB_MCP_CONNECTION_STRING for caching.

{
  "mcpServers": {
    "youtube": {
      "command": "npx",
      "args": ["-y", "@kirbah/mcp-youtube"],
      "env": {
        "YOUTUBE_API_KEY": "AIzaSyYOUR_KEY_HERE"
      }
    }
  }
}
4

Restart Claude Desktop

Fully quit and relaunch Claude Desktop so it picks up the new MCP server. The YouTube tools will appear in the tool panel.

5

Verify with a simple prompt

Ask Claude to search for a YouTube video or fetch transcript for a known video ID to confirm everything is wired up correctly.

YouTube Examples

Client configuration

Claude Desktop configuration with a YouTube API key and optional MongoDB caching.

{
  "mcpServers": {
    "youtube": {
      "command": "npx",
      "args": ["-y", "@kirbah/mcp-youtube"],
      "env": {
        "YOUTUBE_API_KEY": "AIzaSyYOUR_KEY_HERE",
        "MDB_MCP_CONNECTION_STRING": "mongodb+srv://user:[email protected]/"
      }
    }
  }
}

Prompts to try

Example prompts covering the key tools: search, transcript, channel stats, trending, and comments.

- "Search for 'machine learning tutorials' and return the top 5 results"
- "Get the transcript for YouTube video dQw4w9WgXcQ"
- "What are the trending videos in the US for the Music category today?"
- "Fetch the top 10 videos from channel UCxxxxxx and analyze their engagement ratios"
- "Get the comments for video ID dQw4w9WgXcQ including reply threads"
- "Show me the channel statistics for channel UCxxxxxx"

Troubleshooting YouTube

API returns 'quotaExceeded' errors

The YouTube Data API v3 has a daily quota of 10,000 units. Enable MongoDB caching by setting MDB_MCP_CONNECTION_STRING to a MongoDB Atlas URI — this caches responses and dramatically reduces quota consumption. You can also request a quota increase in the Google Cloud Console.

Tools like searchVideos return 'API key required' errors

Most tools require YOUTUBE_API_KEY to be set. The server falls back to transcript-only mode without a key. Create a YouTube Data API v3 key in Google Cloud Console and add it to the env block in your client config.

getTranscripts fails for some videos

Not all YouTube videos have captions enabled. Auto-generated captions are available for many videos; manually uploaded captions are more reliable. Try specifying a language code (e.g., 'en') in the tool call. If no captions exist, the tool will return an error.

Frequently Asked Questions about YouTube

What is YouTube?

YouTube is a Model Context Protocol (MCP) server that get detailed information about multiple youtube videos. returns comprehensive data including video metadata, statistics, and content details. use this when you need complete information about specific It connects AI assistants to external tools and data sources through a standardized interface.

How do I install YouTube?

Install via npm with the command: npx -y @kirbah/mcp-youtube. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with YouTube?

YouTube works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is YouTube free to use?

Yes, YouTube is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Search & Data Extraction MCP Servers

Explore all search & data extraction servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-youtube": { "command": "npx", "args": ["-y", "@kirbah/mcp-youtube"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use YouTube?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides