ask_about_youtube_video
Answers a question about the video or provides a general description if no question is asked.
LABSCO SUMMARY
A video stops being an hour you have to spend and becomes a source you can question.
The work happens at Gemini, so the key and the model named in GEMINI_MODEL_NAME decide both what the answers cost you and how good they are. The tool list is read-only over a URL: nothing clips, downloads or exports a transcript, and the output is always text about the video. extract_key_moments is the one that changes a workflow — timestamps with descriptions give you somewhere to jump to instead of a paragraph to trust.
What it is
A Gemini Vision wrapper for YouTube URLs: summary, question answering and key-moment extraction over a video you name, returned as text.
What you get
- summarize_youtube_video summarises a video from its URL, at a summary_length you choose.
- ask_about_youtube_video answers a specific question about the video, and returns a general description when no question is passed.
- extract_key_moments returns key moments as timestamps with descriptions, as many as number_of_moments asks for.
- list_supported_models lists the Gemini models that support the generateContent method, which is what the other tools call.
Requirements
A Gemini API key in GEMINI_API_KEY and a model name in GEMINI_MODEL_NAME — list_supported_models returns the models that support generateContent, which is what summarize_youtube_video, ask_about_youtube_video and extract_key_moments call.
Setup effort
One command plus a key — npx -y @smithery/cli install @minbang930/youtube-vision-mcp --client claude, then supply credentials
USE CASES
01
Deciding whether an hour-long talk is worth the hour
Get the summary at the length you want, then take the key moments with timestamps so you can watch only the parts that matter.
02
Getting the one answer you needed out of a tutorial
Ask the specific question instead of watching for the part that answers it; with no question passed, the same tool returns a general description.
4 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
extract_key_moments
Extracts key moments (timestamps and descriptions) from a given YouTube video.
list_supported_models
Lists available Gemini models that support the 'generateContent' method.
summarize_youtube_video
Generates a summary of a given YouTube video URL using Gemini Vision API.
BEFORE YOU INSTALL
What to know first
Tools you get
4 tools when we connected. summary_length and number_of_moments are optional arguments of summarize_youtube_video and extract_key_moments, not tools.
Requires
- npx on PATH
- Node.js 18 or later
- GEMINI_API_KEY in your environment
CONTEXT COST
Light Standing cost
Rated by the size of the 4 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
Claude Desktop — Smithery
TERMINAL
npx -y @smithery/cli install @minbang930/youtube-vision-mcp --client claudeMCP Clients
Any MCP client — npx
ANY MCP CLIENT — NPX · JSON
{
"mcpServers": {
"youtube-vision": {
"command": "npx",
"args": [
"-y",
"youtube-vision"
],
"env": {
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"GEMINI_MODEL_NAME": "gemini-2.0-flash"
}
}
}
}
