Flashcards Open Source App

OfficialdeprecatedLive

by kirill-markin · TypeScript

Read, write, and conversationally review open-source flashcards through split read/write MCP tools.

Flashcards Open Source App (MCP Server)

This MCP server provides split read/write tools to read, write, and conversationally review open-source flashcards. It targets open study across iOS, Android, and web, supporting workflows for spaced-repetition review and flashcard content improvement with AI.

🛠️ Key Features

Split read/write MCP tools for flashcards
Conversational flashcard review
AI-powered study and review
External agent API for terminal and AI-agent workflows

🚀 Use Cases

Daily study and exam preparation
Vocabulary learning and technical terms memorization
Spaced-repetition review
Terminal/AI-agent driven flashcard workflows

⚡ Developer Benefits

External agent API suitable for terminal and AI-agent integrations
Tooling oriented around read/write and conversational review
Cross-platform scope: iOS, Android, and web

⚠️ Limitations

Source data does not list tool counts, authentication details, or exact data storage/sync implementation.

flashcardsstudylearningspaced repetitionopen-source

Topics

anki-alternativeawsedtechflashcardsfsrsindexeddbioslocal-firstoffline-firstpostgresqlreactself-hostedspaced-repetitionsqliteswiftuisynctypescriptwebandroidkotlin

README.md3 KBView on GitHub

Nibomo

AI-powered open-source flashcards app for iOS, Android, and web.

Nibomo screenshots

Nibomo (formerly Flashcards Open Source App) is an open-source AI-powered flashcards app built for serious daily study on iOS, Android, and the web. Use it to prepare for exams, learn vocabulary, memorize technical terms and facts, improve your material with AI, and review with spaced repetition. The project also includes an external agent API for terminal and AI-agent workflows.

Available on

iOS
Android
Web
MCP server: https://mcp.nibomo.com/mcp
Agent API: https://api.flashcards-open-source-app.com/v1/

Card scheduling

Card scheduling uses FSRS-based spaced repetition. Detailed scheduling rules live in docs/fsrs-scheduling-logic.md.

MCP connector

The hosted MCP server is available at https://mcp.nibomo.com/mcp and publishes to MCP registries under com.nibomo/flashcards. It exposes seven tools, most of them workspace-scoped: list_workspaces, sql_query, sql_execute, get_guide, next_review_card, reveal_answer, and submit_review.

The dedicated review tools support one-question-at-a-time conversations and idempotent FSRS scheduling. See conversational reviews for the contract shared by MCP, the in-app chat, and the Agent API, and for voice-session examples. ChatGPT Voice currently does not invoke apps/MCP; these tools do not remove that external limitation.

Interactive clients authenticate with OAuth 2.1 authorization code + PKCE and Dynamic Client Registration. Headless clients can use an fca_ Bearer token.

The former address https://mcp.flashcards-open-source-app.com/mcp still serves the same server, so existing client configurations keep working.

Docs

License

This project is licensed under the MIT License - see the LICENSE file for details.

Author

Kirill Markin

Install

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://mcp.flashcards-open-source-app.com/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "flashcards": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.flashcards-open-source-app.com/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.