
MCP Flashcards
An MCP server for creating, studying, and organizing flashcard decks programmatically with features like spaced repetition and statistics tracking.
README
MCP Flashcards
MCP server for managing flashcards - create, study, and organize flashcard decks programmatically.
Features
- Create and manage flashcard decks
- Add, edit, and delete cards
- Study mode with spaced repetition
- Import/Export decks
- Statistics tracking
- Full MCP integration
- NEW: UI workflow integration for Claude Desktop
- NEW: Human-in-the-loop UI prompts
- NEW: Workflow session management
Installation
npm install @no-smoke/mcp-flashcards
Configuration
Add to your MCP settings:
{
"mcpServers": {
"flashcards": {
"command": "npx",
"args": ["@no-smoke/mcp-flashcards"],
"env": {
"FLASHCARDS_DATA_DIR": "./flashcards-data"
}
}
}
}
Usage
Create a deck
await createDeck({
name: "JavaScript Basics",
description: "Fundamental JavaScript concepts"
});
Add cards
await addCard({
deckId: "deck-id",
question: "What is a closure?",
answer: "A function that has access to variables in its outer scope"
});
Study mode
const card = await getNextCard({ deckId: "deck-id" });
await markCard({ cardId: card.id, correct: true });
UI Workflow Integration (v1.1.0)
The Flashcards MCP server now includes UI workflow capabilities that enable human-in-the-loop interactions directly within Claude Desktop.
Key Features
- Start Workflow Session: Initialize a UI workflow session for flashcard operations
- Human-in-the-Loop Prompts: Get user input for deck creation, card addition, and study sessions
- Update Session State: Manage workflow state and progress
- Get Session Status: Check current workflow status and state
Using UI Workflows
Start a Workflow Session
await startFlashcardSession({
type: "create_deck", // or "study", "import"
metadata: {
deckName: "JavaScript Advanced Concepts"
}
});
Show UI Prompt
await showFlashcardPrompt({
sessionId: "session-id",
promptType: "card_content",
data: {
currentStep: 1,
totalSteps: 5,
deckName: "JavaScript Advanced Concepts"
}
});
Update Session
await updateFlashcardSession({
sessionId: "session-id",
updates: {
step: 2,
cardsAdded: 1
}
});
Workflow Types
- create_deck: Interactive deck creation workflow
- study: Guided study session with UI prompts
- import: File import workflow with user confirmation
UI Components
The workflow system uses MCP's ui_textarea
and ui_select
elements to:
- Collect card content from users
- Get user decisions on study session results
- Confirm import operations
- Display progress through multi-step workflows
Documentation
- 📚 UI Workflow Documentation - Complete guide to UI workflows
- 🔧 UI Tools Reference - Quick reference for UI tools
- 🔄 Migration Guide - Upgrade from v1.0.0 to v1.1.0
- 📦 Release Notes - Version history and changelog
- 📋 Changelog - Detailed change history
Development
# Clone the repository
git clone https://github.com/No-Smoke/mcp-flashcards.git
cd mcp-flashcards
# Install dependencies
npm install
# Build
npm run build
# Run tests
npm test
# Start development server
npm run dev
License
MIT License - see LICENSE file for details
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.