Flashcard AI MCP
This MCP server lets you create and manage flashcard decks, run quiz sessions, and view study statistics.
create_deck: Create a new flashcard deck, optionally with initial cards supplied as JSON{front, back}objects.add_card: Add a flashcard to a deck with front, back, optional tags, and hint; the description says it creates the deck if it does not exist.quiz_session: Start a quiz from a deck in standard, reverse, or mixed mode, returning cards due for review with SM-2 scheduling.get_stats: Get deck statistics and optionally record quiz results as JSON{card_id, rating}with ratings 0ā5.Basic usage requires no authentication; optional API keys and free-tier rate limits are supported.
Flashcard Ai MCP
MEOK AI Labs ā Create study flashcards from text
MEOK AI Labs ā Create study flashcards from text.
š Quick Start
# Install via pip
pip install flashcard_ai_mcp
# Or install via Smithery
npx -y @smithery/cli@latest install flashcard-ai-mcp --client claudeRelated MCP server: Quiz Generator AI MCP
⨠Features
MCP protocol compliant
Easy installation
Well-documented API
Production-ready
Active maintenance
š Documentation
š”ļø Compliance
This MCP server is built with EU AI Act compliance built-in:
ā Article 9 ā Risk Management System
ā Article 13 ā Transparency & Instructions for Use
ā Article 15 ā Bias Detection & Testing
ā Article 26 ā FRIA Support (where applicable)
ā Article 50 ā AI Content Watermarking (where applicable)
Need help getting compliant? Book a free 15-min diagnostic ā
How MEOK charges
MEOK has no subscriptions and no tiers. You pay per job, and only when the agreed artifact has been delivered to you. There is no public price list. See https://meok.ai/pricing.
This repository's source is MIT-licensed and free to self-host.
š¤ Part of the MEOK Ecosystem
This server is part of the MEOK AI Labs ecosystem ā 300+ MCP servers for sovereign AI governance.
Domain | Purpose |
EU AI Act compliance marketplace | |
AI safety & monitoring | |
Sovereign AI platform | |
Legacy modernization |
š License
MIT Ā© CSOAI-ORG
Pairs with MEOK Governance Suite
Build something that touches users? You need compliance. MEOK ships 38 governance MCPs that drop in alongside this tool ā EU AI Act, DORA, NIS2, CRA, GDPR, ISO 42001, FDA SaMD, MDR, Basel, MiFID II, MiCA, COPPA, and more.
# One-shot install of the governance pack
npx meok-setup --pack governanceā Full catalogue: councilof.ai ā MEOK AI Labs: meok.ai
Configuration
Add to your claude_desktop_config.json (Claude Desktop) or your MCP client config:
{
"mcpServers": {
"flashcard-ai-mcp": {
"command": "uvx",
"args": ["flashcard-ai-mcp"]
}
}
}Or: pip install flashcard-ai-mcp then run the flashcard-ai-mcp command (stdio transport).
Examples
Once configured, ask your assistant, for example:
"Use
create_deckto ā¦""Use
add_cardto ā¦""Use
quiz_sessionto ā¦"
Available Tools
4 toolsadd_cardD
Add a flashcard to an existing deck. Creates the deck if it doesn't exist.
Behavior: This tool generates structured output without modifying external systems. Output is deterministic for identical inputs. No side effects. Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.
When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results.
Args: deck_name (str): The deck name to analyze or process. front (str): The front to analyze or process. back (str): The back to analyze or process. tags (str): The tags to analyze or process. hint (str): The hint to analyze or process. api_key (str): The api key to analyze or process.
Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent ā calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.
Inputs: back (required), front (required), deck_name (required), hint, +2 more. Returns: result
create_deckD
Create a new flashcard deck. Optionally provide initial cards as JSON array of {front, back} objects.
Behavior: This tool generates structured output without modifying external systems. Output is deterministic for identical inputs. No side effects. Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.
When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results.
Args: name (str): The name to analyze or process. description (str): The description to analyze or process. cards_json (str): The cards json to analyze or process. api_key (str): The api key to analyze or process.
Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent ā calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.
Inputs: name (required), api_key, cards_json, description. Returns: result
get_statsA
Get deck statistics and optionally record quiz results. Results format: JSON array of {card_id, rating} where rating is 0-5 (SM-2 scale).
Behavior: This tool is read-only and stateless ā it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.
When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results.
Args: deck_name (str): The deck name to analyze or process. record_results (str): The record results to analyze or process. api_key (str): The api key to analyze or process.
Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent ā calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.
Inputs: deck_name (required), api_key, record_results. Returns: result
quiz_sessionC
Start a quiz session from a deck. Modes: standard (front->back), reverse (back->front), mixed. Returns cards due for review with SM-2 scheduling.
Behavior: This tool is read-only and stateless ā it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.
When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results.
Args: deck_name (str): The deck name to analyze or process. count (int): The count to analyze or process. mode (str): The mode to analyze or process. api_key (str): The api key to analyze or process.
Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent ā calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.
Inputs: deck_name (required), mode, count, api_key. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogā¦
TDQS
Scored across 4 tools
Each tool has a clear, distinct purpose: adding a card, creating a deck, retrieving stats, and starting a quiz. No overlap in functionality.
Most tool names follow a verb_noun pattern (add_card, create_deck, get_stats). 'quiz_session' is slightly less conventional but still intelligible and consistent in style.
4 tools cover the core flashcard workflow (create deck, add card, quiz, stats). Slightly minimal but well-scoped for a focused server.
Missing essential operations like editing or deleting cards/decks, and listing existing decks or cards. Users cannot modify or remove content, which is a significant gap.
Maintenance
Related MCP Connectors
MCP server for Flux AI image generation
Markdown-based note-taking with a hosted MCP server. Your notes serve you and your AI.
AI tool directory MCP server, live since July 2026. Tools, agents, models, companies, services.
MCP server for Qwen Image 3 AI image generation
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceNote Taking AI - MCP server providing AI-powered tools and automation by MEOK AI Labs6 npm32 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceQuiz Generator AI - MCP server providing AI-powered tools and automation by MEOK AI Labs2 npm35 PyPIMIT
- AlicenseNot gradedqualityDmaintenanceLocal Leitner flashcard MCP server enabling AI clients to create decks, manage cards, study with spaced repetition, and track progress.MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server for making flashcards with your agents and being quizzed on them using SM-2 spaced repetition.7 npmMIT