Skip to main content
Glama

Notion-Anki MCP Server

by bakhruhk

Notion-Anki MCP Server

A Model Context Protocol (MCP) server that automatically generates Anki flashcards from Notion pages. This tool extracts questions and answers from Notion toggle blocks and converts them into structured Anki cards using OpenAI's API, with real-time import via AnkiConnect.

Use Cases

  • Students: Convert study notes from Notion into flashcards for spaced repetition
  • Professionals: Transform training materials and documentation into memorable cards
  • Educators: Quickly create quiz content from lesson plans
  • Researchers: Convert paper summaries and key concepts into study materials

Features

  • Notion Integration: Extracts content from Notion pages via official API
  • Smart Parsing: Recognizes toggle blocks as question-answer pairs
  • AI Enhancement: Uses OpenAI to refine and improve flashcard quality
  • Real-time Import: Automatically adds cards to Anki via AnkiConnect
  • MCP Protocol: Works with MCP-compatible clients like Claude Desktop

Prerequisites

Before setting up this project, ensure you have:

  1. Notion API Access
  2. OpenAI API Access
    • Sign up for OpenAI API
    • Create an API key with sufficient credits
  3. Anki Setup
    • Install Anki desktop application
    • Install AnkiConnect add-on
    • Keep Anki running during flashcard generation
  4. Python Environment
    • Python 3.8 or higher
    • pip package manager

Quick Start

1. Clone the Repository

git clone https://github.com/yourusername/notion-anki-mcp.git cd notion-anki-mcp

2. Install Dependencies

pip install -r requirements.txt

3. Environment Configuration

cp .env.example .env

Edit .env with your API keys:

NOTION_API_KEY=your_notion_api_key_here OPENAI_API_KEY=your_openai_api_key_here

4. Start the MCP Server

python server.py

How to Structure Your Notion Pages

For the tool to work effectively, structure your Notion pages as follows:

Toggle Block Format

Create toggle blocks where:

  • Toggle title = Your question
  • Toggle content = The answer/explanation

Example structure:

📝 Machine Learning Concepts 🔽 What is supervised learning? Supervised learning is a type of machine learning where... - Uses labeled training data - Learns mapping from inputs to outputs - Examples: classification, regression 🔽 What's the difference between classification and regression? Classification predicts categories/classes while regression predicts continuous values...

Supported Content Types

Within toggle blocks, the tool supports:

  • Plain text paragraphs
  • Bulleted lists
  • Numbered lists
  • Basic formatting (bold, italic, etc.)

Usage

  1. Configure your MCP client to connect to this server
  2. Use the available tools:
    • search_page: Find a Notion page by name
    • extract_page_content: Extract questions and answers from a page
    • generate_flashcards: Create and import Anki cards

Direct Python Usage

import asyncio from server import search_notion_page, fetch_page_content, generate_flashcards_gpt async def create_flashcards(page_name): # Search for the page page_result = await search_notion_page(page_name) if not page_result: print(f"Page '{page_name}' not found") return # Extract content topics, content = await fetch_page_content(page_result['page_id']) # Generate and import flashcards cards = await generate_flashcards_gpt(page_name, topics, content) print(f"Created {len(cards)} flashcards for '{page_name}'") # Run the example asyncio.run(create_flashcards("Your Page Name"))

API Reference

MCP Tools

search_page

Searches for a Notion page by name.

Parameters:

  • page_name (string): The title of the Notion page to search for

Returns:

{ "status": "success", "page_name": "Page Title", "result": { "result": "Found", "page_id": "page-uuid", "link": "https://notion.so/..." } }
extract_page_content

Extracts questions and answers from a Notion page.

Parameters:

  • page_id (string): The UUID of the Notion page

Returns:

{ "status": "success", "topics": ["Topic 1", "Topic 2"], "content": { "Question 1?": "Answer 1...", "Question 2?": "Answer 2..." } }
generate_flashcards

Creates Anki flashcards from extracted content.

Parameters:

  • page_name (string): Name for the Anki deck
  • topics (array): List of topics/headings from the page
  • content (object): Question-answer pairs

Returns:

{ "status": "created", "cards": [...], "message": "Created flashdeck and cards for 'Page Name' in Anki" }

Troubleshooting

Common Issues

"Page not found" Error

  • Ensure the page name matches exactly (case-sensitive)
  • Verify your Notion integration has access to the page
  • Check that the page is in a shared workspace

"AnkiConnect not responding" Error

  • Make sure Anki desktop is running
  • Verify AnkiConnect add-on is installed and enabled
  • Check that Anki isn't in review mode or showing a dialog

"OpenAI API Error" Error

  • Verify your OpenAI API key is correct and active
  • Check your API usage limits and billing
  • Ensure you have access to the GPT-4 models

Empty flashcards generated

  • Check that your Notion page uses the toggle block format
  • Ensure toggle blocks contain text content
  • Verify the page has actual content, not just headers

Debug Mode

Enable debug logging by modifying server.py:

import logging logging.basicConfig(level=logging.DEBUG)

Contributing

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

License

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

Acknowledgments


Made with ❤️ for better learning and knowledge retention

-
security - not tested
A
license - permissive license
-
quality - not tested

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

Automatically generates Anki flashcards from Notion pages by extracting questions and answers from toggle blocks. Uses OpenAI to enhance card quality and imports them directly into Anki via AnkiConnect for spaced repetition learning.

  1. Use Cases
    1. Features
      1. Prerequisites
        1. Quick Start
          1. 1. Clone the Repository
          2. 2. Install Dependencies
          3. 3. Environment Configuration
          4. 4. Start the MCP Server
        2. How to Structure Your Notion Pages
          1. Toggle Block Format
          2. Supported Content Types
        3. Usage
          1. Via MCP Client (Recommended)
          2. Direct Python Usage
        4. API Reference
          1. MCP Tools
        5. Troubleshooting
          1. Common Issues
          2. Debug Mode
        6. Contributing
          1. License
            1. Acknowledgments

              Related MCP Servers

              • -
                security
                F
                license
                -
                quality
                An MCP server that enables AI assistants like Claude to interact with Anki flashcard decks, allowing users to create, manage, and update flashcards through natural language conversations.
                Last updated -
                7
                TypeScript
              • A
                security
                F
                license
                A
                quality
                A Model Context Protocol server that enables LLMs to interact with Anki flashcard software through AnkiConnect, allowing for creation and management of flashcards, decks, and note types.
                Last updated -
                10
                53
                98
                TypeScript
                • Apple
              • A
                security
                A
                license
                A
                quality
                A TypeScript-based server that integrates with Anki via the AnkiConnect plugin, allowing you to manage flashcard decks, note models, and create Anki notes using natural language.
                Last updated -
                3
                1
                67
                JavaScript
                MIT License
                • Apple
              • -
                security
                A
                license
                -
                quality
                A Model Context Protocol server that allows LLMs to interact with Anki flashcard software, enabling functions like creating decks, adding notes, searching cards, and managing flashcard content through natural language.
                Last updated -
                53
                1
                JavaScript
                MIT License

              View all related MCP servers

              MCP directory API

              We provide all the information about MCP servers via our MCP API.

              curl -X GET 'https://glama.ai/api/mcp/v1/servers/bakhruhk/notion-anki-mcp'

              If you have feedback or need assistance with the MCP directory API, please join our Discord server