acornonaut-mcp

acornonaut-mcp

AI-powered YouTube playlist to flashcards with spaced repetition (SM-2 algorithm). 18 tools for playlist management, semantic search, and Anki export.

Category
访问服务器

README

Acornonaut MCP Server

MCP

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:

  1. On first connection, your browser opens automatically
  2. Sign in to Acornonaut (or create a free account)
  3. Grant MCP access
  4. 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

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选