edutube-mcp
Uses Google Gemini models for multimodal content analysis and structured lesson generation, including dialogue with Arabic translations, key expressions, vocabulary, cultural/pronunciation notes, and quizzes, with automatic model rotation on quota exhaustion.
Imports YouTube playlists or single videos, resolves video metadata, extracts exact frames, and analyzes audio and visuals to produce structured lessons, quizzes, vocabulary, and lesson notes.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@edutube-mcpExtract lessons and quizzes from this playlist: https://youtube.com/playlist?list=PLabc"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Edutube MCP
🌐 Project site (GitHub Pages): https://engmohammeda.github.io/edutube-mcp/ — includes a live explorer of real extracted lessons.
Turn YouTube playlists and videos into structured lessons, analyses, frames and quizzes — with Google Gemini and automatic model rotation.
MCP stdio server + CLI for AI agents and LMS pipelines. Paste a playlist URL and get back per-lesson JSON: verbatim dialogue with Arabic translations, key expressions, vocabulary, cultural/pronunciation notes, and a 10-question quiz — extracted from the actual audio and visuals, not just captions.
playlist URL ──▶ Edutube ──▶ lesson-01.json … lesson-NN.json + lessons-all.jsonFeatures
Playlist import by URL — paste any YouTube playlist URL (or playlist id, or a single video URL). Entries resolve via the YouTube Data API when
YOUTUBE_API_KEYis set, otherwise automatically viayt-dlp --flat-playlist(no extra key needed).Structured lesson extraction — built-in LMS schema (dialogue / key_expressions / global_vocabulary / lesson_notes / quiz) with a custom-schema option for your own format.
Long-video pipeline with windowed fallback — full-video pass first; if that fails (quota, deadlines, very long VODs) it automatically switches to 150-second windowed extraction with merge & dedupe.
Automatic model rotation — every Gemini model has its own free-tier quota pool. On
429 RESOURCE_EXHAUSTEDthe same request transparently retries on the next available model. The model catalogue is discovered live from the Gemini API, so new models (e.g.gemini-3.6-flash,gemini-3.7-*) join the rotation without code changes.Multimodal analysis tools —
analyze_youtube_video(audio + visuals),analyze_youtube_video_audio(speech-first), exact JPEG frame extraction withyt-dlp+ffmpeg, metadata via YouTube Data API.Long VODs & sessions — task-based
analyze_long_youtube_video, reusablesessionIdfollow-ups, and compatibility background jobs (start_long_youtube_analysis→ poll → result → cancel).Resume-safe batches — already-valid lesson files are skipped; interrupted runs continue where they stopped.
CLI mode —
edutube-mcp extract <url>works without any MCP client.
Related MCP server: YT-NINJA
Requirements
Node.js ≥ 20
A Google Gemini API key (
GEMINI_API_KEY)Optional:
YOUTUBE_API_KEY(metadata tool + faster playlist import)Optional but recommended:
yt-dlpandffmpegon PATH (orYT_DLP_PATH)
Quick Start (MCP client)
{
"mcpServers": {
"edutube": {
"command": "npx",
"args": ["-y", "@engmohammeda/edutube-mcp"],
"env": {
"GEMINI_API_KEY": "your_gemini_key_here",
"YOUTUBE_API_KEY": "optional_youtube_key_here"
}
}
}
}From source:
git clone https://github.com/engmohammeda/edutube-mcp.git
cd edutube-mcp
npm install && npm run build
cp .env.example .env # fill GEMINI_API_KEY
npm start # MCP stdio serverQuick Start (CLI)
# extract a whole playlist into ./edutube-output
edutube-mcp extract "https://www.youtube.com/playlist?list=PL..." --out ./edutube-output --max 20
# or a single video
edutube-mcp extract "https://www.youtube.com/watch?v=VIDEO_ID" --out ./lessonsStdout is clean JSON (progress goes to stderr), so it pipes straight into scripts and LMS importers.
Tools (15)
Tool | Purpose |
| Paste a playlist/video URL → background job that writes structured lessons to |
| Poll, fetch, cancel edutube jobs |
| Multimodal analysis (audio + visuals), custom prompts & JSON schemas, clip windows |
| Speech-first analysis with transcript segments |
| Exact high-res JPEG frame at a timestamp (optional Gemini timestamp refinement) |
| Normalized metadata via YouTube Data API |
| Inspect local yt-dlp/ffmpeg/temp support |
| Long VODs as an MCP task; returns reusable |
| Follow-up questions against a cached session |
| Compatibility job workflow for clients with fixed timeouts |
Configuration
Variable | Purpose |
| required |
| optional (metadata + playlist via Data API) |
| preferred model (default |
| optional explicit rotation order, comma-separated |
| default lesson output directory |
| explicit yt-dlp executable |
Client Integrations
Claude Code
claude mcp add edutube --transport stdio -- node /path/to/edutube-mcp/dist/index.jsCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"edutube": {
"command": "node",
"args": ["/path/to/edutube-mcp/dist/index.js"],
"env": { "GEMINI_API_KEY": "..." }
}
}
}Codex (~/.codex/config.toml)
[mcp_servers.edutube]
command = "node"
args = ["/path/to/edutube-mcp/dist/index.js"]
env = { GEMINI_API_KEY = "..." }Documentation
Privacy & Limits
Media, URLs and prompts are sent to Google Gemini. Free-tier keys have small per-model daily quotas (~20 requests/day/model); automatic rotation spreads work across all models on your key. For production batches use a paid (pay-as-you-go) key. Private, age-restricted, DRM or region-blocked videos may fail. You are responsible for complying with YouTube and Gemini terms.
License
MIT — see LICENSE.
العربية
Edutube MCP — حوِّل قوائم تشغيل وفيديوهات يوتيوب إلى دروس مهيكلة جاهزة للاستيراد في LMS: حوار كامل مع الترجمة العربية، التعبيرات المفتاحية، المفردات مع أمثلة إلزامية، ملاحظات ثقافية/نطق بالعربية، واختبار من 10 أسئلة بأنواع متعددة — مستخرج من الصوت والصورة فعليًا وليس من الترجمة النصية فقط.
أبرز الميزات:
استيراد قائمة تشغيل بلصق الرابط فقط عبر أداة
start_edutube_extraction(أو أمر CLI edutube-mcp extract)، مع استئناف تلقائي يتخطى الدروس المكتملة.تدوير تلقائي بين نماذج Gemini: عند استنفاد حصة أي نموذج (429) يُعاد الطلب على النموذج التالي تلقائيًا، مع اكتشاف ديناميكي لأي نماذج جديدة متاحة لمفتاحك.
مسار فيديو طويل + بديل نوافذ 150 ثانية عند الفشل، ودمج وإزالة تكرار.
15 أداة MCP تشمل التحليل متعدد الوسائط، استخراج إطارات JPEG دقيقة، البيانات الوصفية، والوظائف الخلفية للعملاء ذات المهل الثابتة.
التشغيل السريع: انسخ .env.example إلى .env وضع GEMINI_API_KEY، ثم npm install && npm run build && npm start، أو استخدم الـCLI مباشرة. راجع التوثيق أعلاه للتفاصيل والربط مع Claude Code وCursor وCodex.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityDmaintenanceTransforms YouTube into a queryable knowledge source with search, video details, transcript analysis, and AI-powered tools for summaries, learning paths, and knowledge graphs. Features quota-aware API access with caching and optional OpenAI/Anthropic integration for advanced content analysis.105901MIT
- FlicenseBqualityDmaintenanceEnables AI-powered YouTube video analysis including transcript management, video summaries, chapter generation, keyword extraction, and playback control. Supports searching videos, retrieving channel/playlist information, and translating transcripts using Google Gemini AI.14
- FlicenseAqualityCmaintenanceEnables analysis of YouTube videos using the Gemini API to generate summaries and answer specific questions via direct URLs. It supports standard videos and shorts, allowing users to interact with video content without requiring manual downloads.54
- AlicenseAqualityBmaintenanceAnalyzes YouTube videos using Google's Gemini API, allowing users to get summaries or ask questions about video content via direct URL input.5202MIT
Related MCP Connectors
Voice-led, FSRS-scheduled flashcards from YouTube, PDFs, web, or text. Auto-graded quizzes.
AI-powered YouTube to flashcards with spaced repetition and Anki export
Provide token-optimized, structured YouTube data to enhance your LLM applications. Access efficien…
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/engmohammeda/edutube-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server