flashcards-mcp
A spaced repetition flashcard MCP server using the FSRS-5 algorithm that provides interactive card review, text-to-speech, and image support.
README
flashcards-mcp
A spaced repetition flashcard MCP server for Claude. Uses the FSRS-5 algorithm (successor to Anki's SM-2) with an interactive card UI, text-to-speech, and image support.
Install
npx (quickest)
npx flashcards-mcp
Add to ~/.claude/.mcp.json:
{
"mcpServers": {
"flashcards": {
"command": "npx",
"args": ["flashcards-mcp"]
}
}
}
curl (auto-configures Claude)
curl -fsSL https://raw.githubusercontent.com/zcsabbagh/flashcards-mcp/main/install.sh | bash
Homebrew
brew tap zcsabbagh/tap
brew install flashcards-mcp
Then add to ~/.claude/.mcp.json:
{
"mcpServers": {
"flashcards": {
"command": "flashcards-mcp"
}
}
}
Usage
After restarting Claude, try:
- "create a deck called Algorithms" — creates a new deck
- "add a card: What is Big O? / A notation for algorithm time complexity" — adds a card
- "get due cards" — opens the interactive flashcard UI
- "get due cards for deck 1" — filters to a specific deck
Keyboard shortcuts (in the flashcard UI)
| Key | Action |
|---|---|
| Space / Enter | Flip card |
| 1-4 | Rate (Again, Hard, Good, Easy) |
| Arrow Left/Right | Previous/Next card |
| V | Toggle voiceover (requires ElevenLabs API key) |
Images
Cards support images on front and back faces:
"add a card with front_image from /path/to/image.png"
"set card 5 front image to https://example.com/photo.jpg"
Text-to-Speech
Add your ElevenLabs API key to the MCP config:
{
"mcpServers": {
"flashcards": {
"command": "npx",
"args": ["flashcards-mcp"],
"env": {
"ELEVENLABS_API_KEY": "sk_..."
}
}
}
}
Tools
| Tool | Description |
|---|---|
create_deck |
Create a new deck |
list_decks |
List all decks with stats |
add_card |
Add a single card (supports markdown, images) |
bulk_add_cards |
Add multiple cards at once |
get_due_cards |
Get due cards with interactive UI |
review_card |
Submit a rating (1-4) |
search_cards |
Search cards by keyword |
get_deck_stats |
Mastery distribution, retention rate |
get_card_image |
Lazy-load card images |
set_card_image |
Add/replace card images |
tts |
Text-to-speech via ElevenLabs |
delete_card |
Delete a card |
delete_deck |
Delete a deck and all its cards |
get_review_history |
Card scheduling history |
How it works
- FSRS-5 algorithm schedules reviews based on stability, difficulty, and elapsed time
- SQLite stores everything locally at
~/.claude/mcp-servers/flashcards/data/flashcards.db - MCP App UI renders an interactive flashcard widget directly in Claude's chat
- Images stored as base64 in the database, lazy-loaded one at a time
- Markdown supported in card content (code blocks, lists, headers, etc.)
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.