mochi-mcp
Enables creating, managing, and reviewing Mochi flashcards via the Model Context Protocol, supporting card CRUD, deck organization, and spaced repetition review.
README
@louis030195/mochi-mcp
MCP (Model Context Protocol) server for Mochi flashcard integration. Create, manage, and review spaced repetition flashcards directly from Claude, ChatGPT, or any LLM that supports MCP.
<div align="center">
💖 Support This Project
If you find this MCP server useful, please consider supporting its development!
👉 Click here to support this project
Your support helps maintain and improve this tool for everyone. Thank you! 🙏
</div>
Features
- 📇 Card Management - Create, read, update, delete flashcards
- 🔍 Search - Find cards by name or content
- 📚 Deck Organization - Manage decks and organize cards
- 🔄 Pagination - Handle large card collections efficiently
- 🧠 Spaced Repetition - Integrate with Mochi's learning algorithm
- ✨ Markdown Support - Rich formatting for card content
Installation
Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on Mac or %APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"mochi": {
"command": "npx",
"args": ["-y", "@louis030195/mochi-mcp"],
"env": {
"MOCHI_API_KEY": "your-mochi-api-key"
}
}
}
}
Claude Code
# Install globally in user scope with API key
claude mcp add -s user mochi npx -e MOCHI_API_KEY=your-mochi-api-key -- -y @louis030195/mochi-mcp
Get Your Mochi API Key
- Go to Mochi Account Settings
- Sign up or log in
- Navigate to Settings → Account
- Copy your API key
Usage
Once configured, you can use natural language to interact with Mochi:
Card Management
- "Create a flashcard about the Krebs cycle"
- "Show me my recent flashcards"
- "Update the card about Python decorators"
- "Delete the card with ID abc123"
Search & Organization
- "Search for cards about machine learning"
- "List all my decks"
- "Create a new deck called 'Spanish Vocabulary'"
- "Find cards containing 'neural networks'"
Study & Review
- "Get the next 20 cards for review"
- "Show me cards from the Biology deck"
Tools
mochi_list_cards
List all Mochi flashcards with pagination support.
Parameters:
bookmark(string, optional): Pagination bookmark from previous responselimit(number, optional): Maximum number of cards to fetch (default: 100)
Returns: List of cards with content, IDs, deck info, review status, etc.
mochi_get_card
Get a specific Mochi flashcard by ID.
Parameters:
card_id(string, required): The ID of the card to retrieve
Returns: Detailed card data including front, back, deck, review history, etc.
mochi_create_card
Create a new Mochi flashcard with front/back content.
Parameters:
name(string, required): The front/question of the cardcontent(string, required): The back/answer of the card (markdown supported)deck_id(string, optional): Optional deck ID to add the card to
Returns: Created card data with ID
mochi_update_card
Update an existing Mochi flashcard.
Parameters:
card_id(string, required): The ID of the card to updatename(string, optional): The front/question of the cardcontent(string, optional): The back/answer of the card (markdown supported)
Returns: Updated card data
mochi_delete_card
Delete a Mochi flashcard by ID.
Parameters:
card_id(string, required): The ID of the card to delete
Returns: Deletion confirmation
mochi_list_decks
List all Mochi decks.
Returns: List of decks with names, IDs, card counts, etc.
mochi_create_deck
Create a new Mochi deck.
Parameters:
name(string, required): The name of the deck
Returns: Created deck data with ID
mochi_search_cards
Search for Mochi flashcards by name or content.
Parameters:
query(string, required): Search querybookmark(string, optional): Pagination bookmark from previous response
Returns: List of matching cards
Development
# Clone the repo
git clone https://github.com/louis030195/mochi-mcp.git
cd mochi-mcp
# Install dependencies
npm install
# Build
npm run build
# Run tests
npm test
# Run locally
MOCHI_API_KEY=your-api-key npm start
API Documentation
See Mochi API Docs for full API details.
License
MIT
Author
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。