Flashcard MCP
Enables users to create, review, and manage flashcards using the SM-2 spaced repetition algorithm for optimized learning. It supports organizing cards into projects and automatically handles review scheduling based on user performance.
README
flashcard-mcp
An MCP server that gives Claude (or any MCP client) the ability to create, review, and manage flashcards with spaced repetition (SM-2 algorithm).
Organize cards into projects, tag them by topic, and let the scheduling algorithm figure out when you need to see each card again.
100% vibecoded.
Blog post
Read about how I use this MCP to learn math: Flashcards MCP
Installation
The server URL is:
https://flashcards.louisarge.com/api/mcp
It works out of the box — just add it as a remote MCP server in your client and sign in with Google when prompted.
Video tutorials
Tools
create_project/list_projects— organize cards into projectsread_memory/write_memory/edit_memory— persistent per-project notes and contextcreate_flashcard/edit_flashcard/list_flashcards/delete_flashcard— manage cardsget_due_flashcards— get cards that are due for reviewreview_flashcard— record how well you remembered (1-4), updates the scheduleget_flashcard_answer— reveal the answer after quizzing yourself
Self-hosting
The api/mcp.ts endpoint runs as a Vercel serverless function, backed by Upstash Redis.
Connect an Upstash Redis database via Vercel's Storage integration — it'll set up KV_REST_API_URL and KV_REST_API_TOKEN automatically.
Firebase setup
Authentication uses Firebase Google Sign-In. You'll need a Firebase project with Google auth enabled.
Server environment variables (set in Vercel):
FIREBASE_PROJECT_ID— Firebase project IDFIREBASE_CLIENT_EMAIL— Firebase service account emailFIREBASE_PRIVATE_KEY— Firebase service account private key, PEM format
Client-side Firebase config lives in api/authorize.ts — update the firebase.initializeApp({...}) block with your own Firebase project credentials.
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。