ZubeidHendricks/youtube-mcp-server

What it solves

This project provides a standardized interface for AI language models to interact with YouTube content. It allows LLMs to search for videos, retrieve transcripts, and gather detailed information about channels and playlists, effectively giving AI agents the ability to 'watch' and analyze YouTube data in real-time.

How it works

It is implemented as a Model Context Protocol (MCP) server. It connects to the YouTube Data API and exposes 10 specific tools that an AI model can call. To handle API quota limits, the server supports multiple fallback API keys, automatically retrying requests with a secondary or tertiary key if the primary one is exhausted.

Who it’s for

Developers building AI agents or using MCP-compatible clients (like Claude Desktop or VS Code) who want their AI to have direct access to YouTube's metadata, search capabilities, and video transcripts.

Highlights

• Comprehensive Toolset: Includes tools for searching videos, fetching transcripts, and analyzing channel metadata.
• Quota Management: Supports up to three API keys to prevent service interruptions due to quota limits.
• Creator Discovery: Features specialized tools to find creator channels based on video mentions and activity filters.
• Flexible Deployment: Can be installed globally via npm, run via npx, or deployed as a Docker container.
• Multi-Client Support: Ready for integration with Claude Desktop and VS Code.