MCP HubMCP Hub
rember

rember-mcp

by: rember

A Model Context Protocol (MCP) server for Rember.

28created 28/02/2025
Visit
Rember
Protocol

📌Overview

Purpose: To provide a seamless way for users to create flashcards using the Model Context Protocol (MCP) with Rember, enhancing their study and retention of information through spaced repetition.

Overview: Rember leverages the Model Context Protocol (MCP) to assist users in generating flashcards from various sources, such as chats and PDFs. The integration with Claude enables effortless conversion of learned information into structured flashcards for effective studying.

Key Features:

  • Create Flashcards from Chats: This feature allows users to generate flashcards directly from their conversations with Claude. When users find valuable information, they can prompt Claude to help them remember it, transforming chat notes into flashcards for review.

  • Create Flashcards from PDFs: Users can also create flashcards from specific sections of PDFs, such as chapters. By simply instructing Claude to generate flashcards from a given chapter, users can customize their study material based on existing documents.


Rember MCP

Allow Claude to create flashcards for you with the official Model Context Protocol (MCP) for Rember. Rember helps you study and remember anything you care about by scheduling spaced repetition reviews.

Features and Examples

  • Create flashcards from your chats — "... I like your answer, help me remember it"
  • Create flashcards from your PDFs — "Create flashcards from chapter 2 of this PDF"

Setup

To run the Rember MCP server using npx, use the following command:

npx -y @getrember/mcp --api-key=YOUR_REMBER_API_KEY

Replace YOUR_REMBER_API_KEY with your actual Rember API key, which you can find in your Settings page: https://rember.com/settings/mcp-api. The API key should follow the format rember_ followed by 32 random characters.

Usage with Claude Desktop

Add the following to your claude_desktop_config.json. See https://modelcontextprotocol.io/quickstart/user for more details.

{
  "mcpServers": {
    "rember": {
      "command": "npx",
      "args": ["-y", "@getrember/mcp", "--api-key=YOUR_REMBER_API_KEY"]
    }
  }
}

Available Tools

  • create_flashcards: Create flashcards with AI. This tool takes a list of notes from Claude and calls the Rember API to generate a few flashcards for each note. After learning something new in your chat with Claude, you can ask "help me remember this," "create a few flashcards," or "add to Rember."

Best Practices for Building MCP Servers

Lessons learned while developing the Rember MCP server:

  • Set up logging to stderr as early as possible; it is essential for debugging.
  • Create a simple MCP tool first and verify Claude can call it properly.
  • Invest time in iterating on the tool description:
    • Include details about your product and its URL to help Claude use the tool properly and answer user questions.
    • Clearly explain what MCP is, avoiding hallucinations about its meaning.
    • Describe the tool inputs thoroughly.
    • Explain what happens after Claude calls the tool—for example, the input notes array is sent to the Rember API, which generates flashcards for each note.
    • Provide examples of how the tool can be used (e.g., creating flashcards from a conversation with Claude or from PDFs).
    • List examples of how users might invoke the tool (e.g., "help me remember this," "add to Rember," "create a few flashcards").
    • Include rules to guide Claude in using the tool appropriately.
  • Use the tool call response strategically since it is not shown directly to users but interpreted by Claude:
    • Specify that on success, the Rember API does not return the number of created flashcards, only the number of created rembs, to prevent Claude hallucinating this information.
    • For users who have reached their monthly limit, instruct Claude to inform them about the Rember Pro subscription option with the relevant URL.
  • Implement retries for transient errors with suitable timeouts.
  • Create unit tests simulating Claude Desktop behavior by calling the Claude API with the system prompt from claude.ai. Each test simulates a chat for manual inspection and includes assertions.

What’s Missing

  • Telemetry and observability to detect issues.
  • More exhaustive error handling.
  • Further iterations on the tool description.
  • Additional automated tests.