Quizlar
Quizlar is the learning MCP server. It turns whatever source the user brings — a YouTube lecture, a PDF, a URL, a textbook passage, or a pasted block of notes — into flashcards, then runs interactive quizzes with FSRS spaced-repetition scheduling so the material actually sticks. Every tool maps one-to-one to something a real learner does: ingest, quiz, track progress, review what's due.
README
Quizlar MCP Server
Voice-led, FSRS-scheduled flashcards from YouTube, PDFs, web, or text. Auto-graded quizzes.
Quizlar's MCP server lets Claude, Cursor, Cline, Windsurf, or any MCP-compatible client:
- Create flashcard decks from YouTube videos, PDFs, web pages, or pasted text
- Run auto-graded quizzes with the same tier-1-exact-match → phonetic → LLM grading pipeline that powers the voice product
- Track memory with FSRS spaced repetition — Quizlar is the scheduler of record, every answer updates real memory state
This repo is the public discovery surface (server.json for the Official MCP Registry + a stdio bundle for clients that need it). The hosted MCP server itself is closed-source and runs at https://mcp.quizlar.app/mcp/.
Listings
- Official MCP Registry —
io.github.quizlar/mcp-serverv1.0.0 - Smithery — https://smithery.ai/servers/quizlar/quizlar
Setup
- Mint an API key at https://quizlar.app/settings/api-keys (format:
sk-qz-<32 chars>). - Pick your client below and paste the snippet.
Cursor
~/.cursor/mcp.json:
{
"mcpServers": {
"quizlar": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.quizlar.app/mcp/",
"--header",
"Authorization:Bearer ${QUIZLAR_API_KEY}"
],
"env": { "QUIZLAR_API_KEY": "sk-qz-..." }
}
}
}
Windsurf
~/.codeium/windsurf/mcp_config.json — Windsurf supports Streamable HTTP natively, no wrapper needed:
{
"mcpServers": {
"quizlar": {
"serverUrl": "https://mcp.quizlar.app/mcp/",
"headers": { "Authorization": "Bearer ${QUIZLAR_API_KEY}" }
}
}
}
Then export QUIZLAR_API_KEY=sk-qz-... in your shell.
Claude Desktop
Open Settings → Connectors → "Add custom connector":
- Name: Quizlar
- URL:
https://mcp.quizlar.app/mcp/ - Add header → Name:
Authorization, Value:Bearer sk-qz-...
Or edit claude_desktop_config.json directly using mcp-remote:
{
"mcpServers": {
"quizlar": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.quizlar.app/mcp/",
"--header",
"Authorization:Bearer ${QUIZLAR_API_KEY}"
],
"env": { "QUIZLAR_API_KEY": "sk-qz-..." }
}
}
}
Cline
Edit cline_mcp_settings.json (Cline → Settings → MCP Servers → "Edit JSON"):
{
"mcpServers": {
"quizlar": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.quizlar.app/mcp/",
"--header",
"Authorization:Bearer ${QUIZLAR_API_KEY}"
],
"env": { "QUIZLAR_API_KEY": "sk-qz-..." }
}
}
}
Detailed steps in llms-install.md.
Smithery
npx -y @smithery/cli@latest install @quizlar/quizlar --client claude
Replace claude with cursor, windsurf, etc. Smithery walks you through pasting your API key.
Tools
22 tools mapped 1:1 to learner verbs:
- Ingest:
create_deck_from_youtube,create_deck_from_pdf,create_deck_from_url,create_deck_from_text,import_shared_deck,get_job_status - Quiz:
quiz_me(composite: build + start in one call),start_quiz,next_card,submit_answer,end_quiz - Review:
get_study_recommendations,get_progress,get_streak,get_analytics - Manage:
list_decks,get_deck,update_deck,delete_deck,add_card,update_card,get_user_profile,update_preferences
Auth
Bearer API key (sk-qz-<32 chars>) is the simplest path and works in every client snippet above. Quizlar also exposes full OAuth 2.1 with Dynamic Client Registration + PKCE at https://mcp.quizlar.app/.well-known/oauth-authorization-server for clients that prefer a browser flow.
Links
- App: https://quizlar.app
- Issues: https://github.com/quizlar/mcp-server/issues
- Stdio bundle source:
bundle/(used to publish to Smithery + any other stdio-only client)
License
MIT for this configuration repo. The hosted MCP server itself is proprietary.
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。