mcpserver.so LogoMCPFly
Submit
YouTube Vision MCP Server logo

YouTube Vision MCP Server

by minbang930

AI/MLGeminiVision APIYouTube

The YouTube Vision MCP server utilizes the Google Gemini Vision API to interact with YouTube videos. It allows users to get descriptions, summaries, answers to questions, and extract key moments from YouTube videos.

View on GitHub

Last updated: N/A

What is YouTube Vision MCP Server?

The YouTube Vision MCP server is a Model Context Protocol server that leverages the Google Gemini Vision API to analyze YouTube videos. It provides tools for describing, summarizing, answering questions, and extracting key moments from videos.

How to use YouTube Vision MCP Server?

The server can be installed via Smithery or manually from source. Using npx is recommended for quick use. Configuration involves setting the Gemini API key and optionally the model name in your MCP client's settings. Available tools can then be used by sending appropriate input data (e.g., YouTube URL, question) and receiving the corresponding output (e.g., summary, answer).

Key features of YouTube Vision MCP Server

  • Analyzes YouTube videos using the Gemini Vision API

  • Provides tools for description, summarization, and key moment extraction

  • Lists available Gemini models supporting generateContent

  • Configurable Gemini model via environment variable

  • Communicates via stdio (standard input/output)

Use cases of YouTube Vision MCP Server

  • Getting descriptions or answering questions about YouTube videos

  • Summarizing YouTube videos for quick understanding

  • Extracting key moments from YouTube videos for efficient review

  • Listing supported Gemini models for informed selection

FAQ from YouTube Vision MCP Server

What is the required Node.js version?

Version 18 or higher is recommended.

Where do I obtain the Google Gemini API Key?

From Google AI Studio or Google Cloud Console.

How do I set the Gemini API key?

Set the GEMINI_API_KEY environment variable in your MCP client's settings file.

What is the default Gemini model?

The default model is gemini-2.0-flash.

Can I use experimental Gemini models in production?

No, models marked as 'Experimental' or 'Preview' are not permitted for production deployment according to the Gemini API Terms of Service.