GitHub Repository

Transform YouTube videos into a compounding knowledge base with transcripts, vision analysis, and agentic search. Works as an MCP server for Claude, Copilot & more.

113 starsPython

Mcptube – Turn YouTube videos into AI-queryable MCP servers

Name: Mcptube – Turn YouTube videos into AI-queryable MCP servers
Availability: InStock
Author: belai

by belai·Mar 3, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidNiche GemSolve My ProblemBig Brain

YouTube + MCP servers means Claude can actually query video lectures semantically.

Strengths

•Semantic search across video transcripts and frames via ChromaDB indexing.
•MCP passthrough design: zero API keys needed on server, client LLM does analysis.
•Dual interface (CLI + MCP server) with BYOK option for deterministic results.

Weaknesses

•Crowded vector-search-over-transcripts space; Cursor, Continue, and other codebase Q&A tools already do similar retrieval.
•Requires ffmpeg + Python 3.12 setup; adoption barrier for non-developers.

Post Description

I built mcptube because I spend a lot of time learning from Stanford and Berkeley lectures on YouTube, and I wanted a better way to interact with the content.

mcptube ingests YouTube videos (transcripts, metadata, frames) and exposes them through both a CLI and an MCP server. You can semantically search transcripts, extract frames at any moment, ask questions about videos, and generate illustrated reports.

It works with Claude Code, VS Code Copilot, Claude Desktop, and any MCP-compatible client. The MCP tools are passthrough — the connected LLM does the heavy lifting, zero API key needed on the server. The CLI also supports BYOK for more deterministic results.

Tech stack: FastMCP, yt-dlp, ChromaDB, LiteLLM, SQLite.

GitHub: https://github.com/0xchamin/mcptube PyPI: https://pypi.org/project/mcptube/

pipx install mcptube --python python3.12