LinuxCommandLibrary
GitHubF-DroidGoogle Play Store

mcptube

YouTube video knowledge engine with transcripts and vision

TLDR

Add a YouTube video to the library
$ mcptube add "[youtube_url]"
copy
Add a video in text-only mode (no frame extraction)
$ mcptube add "[youtube_url]" --text-only
copy
List all videos in the library
$ mcptube list
copy
Search across video transcripts
$ mcptube search "[query]"
copy
Ask a question about video content
$ mcptube ask "[question]"
copy
Generate a report on a specific topic
$ mcptube report [video_query] --focus "[topic]"
copy
Start the MCP server
$ mcptube serve --stdio
copy

SYNOPSIS

mcptube \<command\> [options]

DESCRIPTION

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.

PARAMETERS

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

CAVEATS

Requires Python 3.12 or 3.13 (ChromaDB is not compatible with Python 3.14) and ffmpeg for frame extraction. Full feature set requires API keys from at least one LLM provider (Anthropic, OpenAI, or Google). The MCP server is currently local-only. Text-only mode is available for cost reduction when vision features are not needed.

HISTORY

mcptube was created by 0xchamin and written in Python. It evolved from a simple transcript search tool into a full video knowledge engine with wiki capabilities, vision-based frame analysis, and MCP server integration for use with AI coding assistants.

SEE ALSO

yt-dlp(1), ffmpeg(1), youtube-dl(1)

Copied to clipboard
Kai