Recall – an MCP server that turns your notes into flashcards

Name: Recall – an MCP server that turns your notes into flashcards
Availability: InStock
Author: tushar-nath

by tushar-nath·Jul 22, 2026·3 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidSolve My ProblemShip It

FSRS scheduling is a smart choice, but Anki already dominates the spaced-repetition market.

Strengths

•Leveraging the new MCP protocol to bridge chatbots and study tools is a clever architectural fit.
•Using FSRS instead of basic SM-2 shows genuine attention to modern spaced-repetition research.
•Support for diverse inputs like handwritten PDFs and Notion pages reduces friction for users.

Weaknesses

•The 'AI makes flashcards' value prop is becoming crowded with Anki add-ons and mobile apps.
•Pricing a niche utility tool immediately after launch creates high friction against free alternatives.

Post Description

I have been bouncing off flashcards because making them by hand has been always a tedious task. Recall runs as an MCP server - you can connect it to Claude or Chatgpt, point our our handwritten or typed notes (PDFs, docs, or even a Notion Page), and it writes Q&A cards straight into a deck. You could even ask Claude or Chatgpt to research on a topic and do the same without having the need to make notes. Then you review them with the FSRS spaced repetition algorithm.

Built it solo over the last 2 weeks. Stack used: Next.js, Drizzle + Neon, ts-fsrs for scheduling

It's a paid product - no card limit tricks, you can see check out the demo before paying

A short demo: [https://youtu.be/zPDFX9490Jo](https://youtu.be/zPDFX9490Jo)

Happy to show the MCP setup works alongside the card generation! Feedbacks are super welcome, and would love to bring in tiny features!