Quizlar

Name: Quizlar
Author: quizlar

@quizlar

关于 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

#flashcards #spaced-repetition #fsrs #study #learning #quiz #education #voice #youtube #pdf

基本信息

分类

其他

传输方式

stdio

发布者

quizlar

提交者

Sangura Sitati

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "quizlar": {
      "url": "https://mcp.quizlar.app/mcp/",
      "headers": {
        "Authorization": "Bearer sk-qz-YOUR_API_KEY"
      }
    }
  }
}

工具

** `create_deck_from_youtube`, `create_deck_from_pdf`, `create_deck_from_url`, `create_deck_from_text`, `import_shared_deck`, `get_job_status`

** `quiz_me` (composite: build + start in one call), `start_quiz`, `next_card`, `submit_answer`, `end_quiz`

** `get_study_recommendations`, `get_progress`, `get_streak`, `get_analytics`

** `list_decks`, `get_deck`, `update_deck`, `delete_deck`, `add_card`, `update_card`, `get_user_profile`, `update_preferences`

概览

What is Quizlar?

Quizlar is a voice-led flashcard and quiz MCP server that uses FSRS spaced repetition to schedule memory reviews. It lets Claude, Cursor, Cline, Windsurf, or any MCP-compatible client create decks from YouTube videos, PDFs, web pages, or pasted text, and run auto-graded quizzes with a tiered grading pipeline (exact-match → phonetic → LLM). It’s ideal for learners and educators who want AI-powered, memory‑optimized study sessions.

How to use Quizlar?

Mint an API key at https://quizlar.app/settings/api-keys (format: sk-qz‑<32 chars>). Then configure your MCP client’s mcpServers to point to https://mcp.quizlar.app/mcp/ with Bearer token authentication. Cursor, Windsurf, Claude Desktop, Cline, and Smithery setup snippets are provided in the README. Windsurf supports Streamable HTTP natively; other clients use mcp-remote as a stdio wrapper.

Key features of Quizlar

Create flashcard decks from YouTube, PDFs, URLs, or text.
Auto‑graded quizzes with exact‑match → phonetic → LLM grading.
FSRS spaced repetition tracks real memory state per answer.
22 tools mapped 1:1 to learner verbs (ingest, quiz, review, manage).
Bearer API key and OAuth 2.1 with PKCE authentication.
Hosted server at mcp.quizlar.app (closed‑source; config repo is MIT).

Use cases of Quizlar

Study YouTube lectures by turning them into spaced‑repetition flashcard decks.
Extract key concepts from PDF textbooks and quiz yourself automatically.
Review web articles with auto‑graded quizzes that adapt to your memory.
Import shared decks and collaboratively track progress with FSRS.
Integrate memory‑aware quizzes into AI‑assisted learning workflows.

FAQ from Quizlar

What is the difference between the hosted server and this repo?

This repo is a public configuration and discovery surface (including a stdio bundle for Smithery). The hosted MCP server itself is closed‑source and runs at https://mcp.quizlar.app/mcp/.

What runtime or dependencies does Quizlar require?

No runtime installation is needed for servers that support Streamable HTTP (e.g., Windsurf). Other clients require npx to run the mcp-remote stdio wrapper. An API key from quizlar.app is mandatory.

Where does my study data live?

Data is stored in the Quizlar app and managed through its API. The hosted MCP server is the scheduler of record — every answer updates real memory state.

How do I authenticate with Quizlar?

Use a Bearer API key (sk-qz‑<32 chars>) in the Authorization header. Quizlar also supports full OAuth 2.1 with Dynamic Client Registration + PKCE for clients that prefer a browser flow.

What transport does Quizlar use?

The server uses Streamable HTTP by default. For stdio‑only clients (e.g., Smithery), a stdio bundle is available in the bundle/ directory and published via the mcp-remote wrapper.