Frequently Asked Questions (FAQ) about MCP Server for YouTube

Q: What is the MCP Server for YouTube? A: The MCP Server for YouTube connects YouTube video processing capabilities to Claude AI via the Model Context Protocol (MCP). It allows you to extract subtitles, screenshots, and other information from YouTube videos for use in AI applications.

Q: What are the prerequisites for using the MCP Server? A: You need yt-dlp and ffmpeg installed, as well as Node.js and npm (for the Node.js installation method) or Docker (for the Docker installation method).

Q: How do I install the MCP Server? A: You can install it via Node.js using npm install -g @novemberde/mcp-youtube or via Docker by pulling the novemberde/mcp-youtube image.

Q: How do I configure Claude to use the MCP Server? A: You need to add the MCP server configuration to your claude_desktop_config.json file, specifying the command and arguments to run the server.

Q: What tools are available in the MCP Server? A: The available tools include download_youtube_url (to download subtitles), search_youtube_videos (to search YouTube videos), and get_screenshots (to capture screenshots from specific timestamps).

Q: How do I use the download_youtube_url tool? A: Provide the YouTube video URL in the url parameter. For example: {"url": "https://www.youtube.com/watch?v=example"}.

Q: How do I use the search_youtube_videos tool? A: Provide a search term in the query parameter and optionally specify the maximum number of results in the max_results parameter. For example: {"query": "how to make pizza", "max_results": 5}.

Q: How do I use the get_screenshots tool? A: Provide the YouTube video URL in the url parameter and an array of timestamps in HH:MM:SS format in the timestamps parameter. For example: {"url": "https://www.youtube.com/watch?v=example", "timestamps": ["00:01:30", "00:05:45"]}.

Q: Where are the screenshots saved? A: The screenshots are saved in a temporary directory, which is automatically cleaned up.

Q: Does the MCP Server handle errors? A: Yes, the server provides descriptive error messages for troubleshooting.

Q: Can I use the MCP Server with the UBOS platform? A: Yes, the MCP Server can be integrated with the UBOS platform to orchestrate complex AI agent workflows. UBOS allows you to connect AI Agents with your enterprise data, build custom AI Agents with your LLM model and Multi-Agent Systems.

Q: How can I contribute to the MCP Server project? A: You can contribute by forking the repository, creating a feature branch, committing your changes, and submitting a pull request.