mcptube 命令

常用示例

说明

mcptube is a YouTube video knowledge engine that extracts metadata, transcripts, and frames from YouTube videos, indexes them for semantic search, and exposes everything as both a CLI tool and an MCP (Model Context Protocol) server. The tool builds a persistent wiki knowledge base that grows richer with each video ingested, rather than treating videos as isolated searchable chunks. It uses scene-change detection instead of fixed-interval sampling to capture high-information-density frames. Search combines FTS5 keyword matching with LLM-powered reasoning for hybrid retrieval. mcptube operates in two modes: CLI mode using your own API keys (Anthropic, OpenAI, or Google) for deterministic results, and MCP passthrough mode where the connected AI assistant analyzes data using its own model, avoiding double-billing.

参数

add _url_ _--text-only_

Add a YouTube video to the library; use --text-only to skip frame extraction

remove _query_

Remove a video from the library

list

List all videos in the library

info _query_

Show detailed information about a video

search _query_

Search across video transcripts

ask _question_

Ask a natural language question about video content

frame _query_ _timestamp_

Extract a frame at a specific timestamp

frame-query _query_ _description_

Find frames matching a visual description

classify _query_

Classify video content

report _query_ _--focus topic_ _--format html_ _-o file_

Generate a report about a video

report-query _topic_ _--tag tag_

Generate a report across videos by topic

discover _topic_

Discover new videos related to a topic

wiki list _--type type_ _--tag tag_

List wiki pages

wiki show _slug_

Display a wiki page

wiki search _query_

Search wiki content

wiki toc

Show wiki table of contents

wiki export _--format html_ _--page slug_

Export wiki pages

serve _--stdio_ _--host host_ _--port port_ _--reload_

Start the MCP server