# Flash

This MCP server lets an AI build flashcards, quiz you by voice, and schedule reviews with FSRS. It connects to Claude Code and other listed clients.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 6
- Author: flash-cards
- License: AGPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/flash-cards/flash
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/flash

## What it does

Flash gives an AI client access to decks through MCP. The client can add cards, run study sessions, and ask questions from a deck, while the server schedules future reviews with FSRS. It is shipped as a single Rust binary and supports importing and exporting Anki `.apkg` decks.

For a self-hosted setup, run the server in Docker and keep its data in the `flash-data` volume. The MCP endpoint is `/mcp`; exposing it beyond the local machine requires a TLS reverse proxy and `FLASH_BASE_URL`. The hosted version can also build cards from files and grade spoken answers. Back up the volume before upgrading, since upgrades move forward only.

## Requirements
- Remote server: `https://flashmemorize.com/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http flash https://flashmemorize.com/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add flash --url https://flashmemorize.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "flash": {
            "url": "https://flashmemorize.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "flash": {
            "type": "http",
            "url": "https://flashmemorize.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http flash https://flashmemorize.com/mcp
```

## When to use it
- turn source material into AI-written flashcards
- quiz yourself from a selected deck
- schedule reviews with FSRS
- move decks through Anki `.apkg` files
- grade spoken answers in the hosted version

## Example prompts
- Quiz me on my `World capitals` deck, one card at a time.
- Create cards from this file and start a study session.
- Show me the cards that are due for review today.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89609
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [Front-End Checklist](https://affpapa.org/en/nevibecode/mcp/front-end-checklist.md) — MCP server · ★ 74569
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89899

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md