YouTube MCP Server logo

YouTube MCP Server

by ZubeidHendricks

A Model Context Protocol (MCP) server implementation for YouTube, enabling AI language models to interact with YouTube content through a standardized interface. It allows AI to access video information, transcripts, and manage channels and playlists.

View on GitHub

Last updated: N/A

What is YouTube MCP Server?

The YouTube MCP Server is a server that provides a standardized interface (MCP) for AI language models to interact with YouTube. It allows AI to access video details, transcripts, channel information, and playlist data.

How to use YouTube MCP Server?

The server can be installed via Smithery or manually using npm. After installation, configure the YOUTUBE_API_KEY environment variable. Then, configure your MCP client (e.g., Claude Desktop or VS Code) to connect to the server using the provided configuration snippets.

Key features of YouTube MCP Server

  • Get video details (title, description, duration, etc.)

  • Retrieve video transcripts with language support and timestamps

  • Manage channel details and list channel videos/playlists

  • Search videos and transcripts across YouTube

  • Manage playlist items and details

Use cases of YouTube MCP Server

  • AI-powered video summarization

  • Intelligent video search and discovery

  • Automated content analysis and tagging

  • AI-driven education and learning platforms

FAQ from YouTube MCP Server

How do I get a YouTube API key?

Go to Google Cloud Console, create or select a project, enable the YouTube Data API v3, create API credentials, and copy the API key.

What is the default language for transcripts?

The default language is 'en' (English), but you can change it using the YOUTUBE_TRANSCRIPT_LANG environment variable.

How do I install the server manually?

Use the command npm install zubeid-youtube-mcp-server.

How do I configure the server for Claude Desktop?

Add the provided JSON configuration block to your Claude Desktop MCP client configuration.

Can I use this server with VS Code?

Yes, you can install it using the provided VS Code install buttons or manually add the configuration to your User Settings (JSON) file or a .vscode/mcp.json file in your workspace.