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 provides access to video information, transcripts, and channel/playlist management.

View on GitHub

Last updated: N/A

What is YouTube MCP Server?

The YouTube MCP Server is a server that allows AI language models to interact with YouTube content using the Model Context Protocol. It provides a standardized interface for accessing video information, transcripts, channel details, and playlist data.

How to use YouTube MCP Server?

The server can be installed via Smithery or manually using npm. It requires a YouTube Data API key and can be configured within an MCP client (e.g., Claude Desktop) or VS Code. Environment variables must be set for the API key and optional transcript language.

Key features of YouTube MCP Server

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

  • Retrieve video transcripts with language support and timestamps

  • Manage channel details, videos, and playlists

  • Search videos and transcripts across YouTube

Use cases of YouTube MCP Server

  • Enabling AI models to summarize YouTube videos

  • Providing context for AI conversations based on video transcripts

  • Building AI-powered search tools for YouTube content

  • Integrating YouTube content into AI-driven applications

FAQ from YouTube MCP Server

What is the Model Context Protocol (MCP)?

MCP is a standardized interface for AI language models to interact with external data sources.

How do I get a YouTube Data API key?

You can obtain an API key from the Google Cloud Console by enabling the YouTube Data API v3 and creating credentials.

What is the purpose of the YOUTUBE_TRANSCRIPT_LANG environment variable?

This variable sets the default language for retrieving video transcripts. If not specified, it defaults to 'en' (English).

Can I use this server with any MCP client?

Yes, as long as the client supports configuring MCP servers with a command and arguments.

Where can I find more information about contributing to the project?

See the CONTRIBUTING.md file in the repository for details on how to contribute.