acornonaut-mcp
AI-powered YouTube playlist to flashcards with spaced repetition (SM-2 algorithm). 18 tools for playlist management, semantic search, and Anki export.
README
Acornonaut MCP Server
AI-powered flashcard generation from YouTube videos — Turn any YouTube playlist into spaced-repetition flashcards and manage your learning library through any MCP-compatible AI client.
This is the official MCP server for Acornonaut, hosted at https://mcp.acornonaut.app.
✨ Features
- 🎥 YouTube to flashcards — AI-generated cards from video transcripts
- 🧠 Spaced repetition — SM-2 algorithm for optimal review scheduling
- 📚 Playlist management — Organize learning content by topic
- 🔍 Semantic search — Find cards across your entire library
- 📦 Anki export — Export decks to Anki format
- 🔐 OAuth 2.0 — Secure, browser-based authentication
🚀 Quick Start
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"acornonaut": {
"url": "https://mcp.acornonaut.app"
}
}
}
Restart Claude Desktop. On first use, your browser will open for OAuth sign-in.
Cursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"acornonaut": {
"url": "https://mcp.acornonaut.app",
"transport": "streamable-http"
}
}
}
Windsurf
Use MCP Server settings:
- Name:
acornonaut - URL:
https://mcp.acornonaut.app - Transport:
streamable-http
Or JSON config:
{
"mcpServers": {
"acornonaut": {
"url": "https://mcp.acornonaut.app",
"transport": "streamable-http"
}
}
}
Continue.dev / Cline
Add to your MCP config:
{
"mcpServers": {
"acornonaut": {
"url": "https://mcp.acornonaut.app"
}
}
}
OpenClaw
{
"mcpServers": {
"acornonaut": {
"url": "https://mcp.acornonaut.app"
}
}
}
🔐 Authentication
Acornonaut MCP uses OAuth 2.0 for secure authentication:
- On first connection, your browser opens automatically
- Sign in to Acornonaut (or create a free account)
- Grant MCP access
- Return to your AI client — you're connected!
No API keys to manage. Tokens are stored securely by your MCP client.
🛠️ Available Tools
| Tool | Description |
|---|---|
| Playlists | |
list_playlists |
List all your playlists with status and progress |
get_playlist |
Get a single playlist with videos and cards |
create_playlist |
Create a new playlist from a YouTube URL |
update_playlist |
Rename or update playlist settings |
delete_playlist |
Permanently delete a playlist and its cards |
| Videos | |
add_video_by_url |
Add a single YouTube video to a playlist |
get_video_cards |
Get all flashcards for a specific video |
get_transcript |
Retrieve the full transcript of a video |
| Cards | |
list_cards |
List paginated flashcards with filters |
get_card |
Get a single card by ID |
create_card |
Create a custom flashcard manually |
update_card |
Edit a card's front, back, or metadata |
delete_card |
Delete a specific card |
search_cards |
Full-text search across all your cards |
| Spaced Repetition | |
review_due_cards |
Get cards due for review today |
answer_card |
Submit review answer and update scheduling |
get_review_stats |
View your review statistics and streaks |
Total: 18 tools
📖 Example Usage
Create a playlist from YouTube
Ask your AI: "Create an Acornonaut playlist from https://www.youtube.com/playlist?list=..."
Search your flashcards
Ask your AI: "Search my Acornonaut cards for 'photosynthesis'"
Review due cards
Ask your AI: "What cards are due for review in Acornonaut today?"
Export to Anki
Ask your AI: "Export my 'Biology 101' playlist from Acornonaut as an Anki deck"
🔗 Links
- Product: https://acornonaut.app
- Documentation: https://acornonaut.app/docs/mcp
- Main repository: https://github.com/zerolve-io/coursecards
- MCP Spec: https://modelcontextprotocol.io
📝 License
MIT License - see LICENSE file.
Built with ❤️ by the Acornonaut team
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。