
Quizlar — voice-powered AI flashcards with spaced repetition
Hooks Claude into Quizlar's spaced-repetition flashcard engine. You can generate decks from YouTube URLs, PDFs, web pages, or pasted text, then run auto-graded quizzes that update FSRS memory schedules in real time. The 22 tools map directly to learner actions: create_deck_from_youtube, start_quiz, submit_answer, get_progress, get_knowledge_gaps. Grading follows the same three-tier pipeline as Quizlar's voice product (exact match, then phonetic, then LLM fallback). Runs as a hosted service at mcp.quizlar.app with Bearer API key auth or full OAuth 2.1 if your client supports it. Reach for this when you want Claude to build study materials from arbitrary content and track retention over time, not just generate one-off Q&A pairs.
- tools
- 22
- auth
- Secret needed
- transport
- HTTP
- last updated
- Apr 30, 2026
Tools
22 toolsPublic tool metadata for what this MCP can expose to an agent.
create_deck
No parameter schema in public metadata yet.
create_deck_from_text
No parameter schema in public metadata yet.
create_deck_from_youtube
No parameter schema in public metadata yet.
create_cards_batch
No parameter schema in public metadata yet.
get_job_status
No parameter schema in public metadata yet.
quiz_meComposite tool that builds a deck and starts a quiz in one call.
Composite tool that builds a deck and starts a quiz in one call.
No parameter schema in public metadata yet.
start_quiz
No parameter schema in public metadata yet.
submit_answer
No parameter schema in public metadata yet.
skip_question
No parameter schema in public metadata yet.
end_quiz
No parameter schema in public metadata yet.
list_decks
No parameter schema in public metadata yet.
get_deck
No parameter schema in public metadata yet.
list_cards
No parameter schema in public metadata yet.
search_decks
No parameter schema in public metadata yet.
search_cards
No parameter schema in public metadata yet.
list_sessions
No parameter schema in public metadata yet.
get_progress
No parameter schema in public metadata yet.
get_study_recommendations
No parameter schema in public metadata yet.
get_learning_velocity
No parameter schema in public metadata yet.
get_knowledge_gaps
No parameter schema in public metadata yet.
get_retention_curves
No parameter schema in public metadata yet.
get_card_difficulty_stats
No parameter schema in public metadata yet.
Sponsors
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/ for OAuth-capable clients, /mcp-apikey/ for apiKey Bearer auth (used by every snippet in this README).
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
Details
- Repository
- github.com/quizlar/mcp-server
- Website
- quizlar.app
- Category
- Media & Entertainment
- Transport
- HTTP
- Auth
- Required
- Registry
- MCP registry, active