Skip to main content
0
N

Notion MCP Advanced

Notion MCP Integration is a lightweight Model Context Protocol (MCP) server that seamlessly integrat

Rating

0.0

Votes

0

score

Downloads

0

total

Price

Free

API key required

Works With

Claude CodeCursorWindsurfVS CodeDeveloper tool

About

Notion MCP Integration

A simple Model Context Protocol (MCP) server that integrates with Notion's API to manage my personal todo list through Claude. This is a basic implementation tailored specifically for my minimalist todo list setup in Notion.

This project is based on danhilse/notion_mcp, which is available under the MIT license.

Important Note

This is a personal project designed for a very specific use case: my simple Notion todo list that has just four properties:

  • Task (title)
  • Checkbox (marks if completed)
  • Description (additional details)
  • Link (URL or reference)

Example Notion Database

While you can use this as a starting point for your own Notion integration, you'll likely need to modify the code to match your specific database structure and requirements.

Features

  • Add new todo items with descriptions and links
  • View all todos
  • Check off tasks as complete
  • Link external resources to tasks

Prerequisites

  • Python 3.10 or higher
  • A Notion account
  • A Notion integration (API key)
  • A Notion database that matches the exact structure described above (or willingness to modify the code for your structure)

Setup

  1. 1.Clone the repository:
bash
git clone https://github.com/yourusername/notion-mcp.git
cd notion-mcp
  1. 1.Set up Python environment:
bash
python -m venv .venv
source .venv/bin/activate  # On Windows use: .venv\Scripts\activate
uv pip install -e .
  1. 1.Create a Notion integration:
  • Go to https://www.notion.so/my-integrations
  • Create new integration
  • Copy the API key
  1. 1.Share your database with the integration:
  • Open your todo database in Notion
  • Click "..." menu → "Add connections"
  • Select your integration
  1. 1.Create a .env file:
env
NOTION_API_KEY=your-api-key-here
NOTION_DATABASE_ID=your-database-id-here
  1. 1.Configure Claude Desktop:
json
{
  "mcpServers": {
    "notion-todo": {
      "command": "/path/to/your/.venv/bin/python",
      "args": ["-m", "notion_mcp"],
      "cwd": "/path/to/notion-mcp"
    }
  }
}

Running the Server

The server can be run in two ways:

  1. 1.Directly from the command line:
bash
# From the project directory with virtual environment activated
python -m notion_mcp
  1. 1.Automatically through Claude Desktop (recommended):
  • The server will start when Claude launches if configured correctly in claude_desktop_config.json
  • No manual server management needed
  • Server stops when Claude is closed

Note: When running directly, the server won't show any output unless there's an error - this is normal as it's waiting for MCP commands.

Usage

Basic commands through Claude:

  • "Show all my todos"
  • "Add a todo: check emails"
  • "Add a todo: review project docs, with link: https://example.com/docs"
  • "Mark todo [ID] as complete"

Limitations

Don't lose this

Three weeks from now, you'll want Notion MCP Advanced again. Will you remember where to find it?

Save it to your library and the next time you need Notion MCP Advanced, it’s one tap away — from any AI app you use. Group it into a bench with the rest of the team for that kind of task and you can pull the whole stack at once.

⚡ Pro tip for geeks: add a-gnt 🤵🏻‍♂️ as a custom connector in Claude or a custom GPT in ChatGPT — one click and your library is right there in the chat. Or, if you’re in an editor, install the a-gnt MCP server and say “use my [bench name]” in Claude Code, Cursor, VS Code, or Windsurf.

🤵🏻‍♂️

a-gnt's Take

Our honest review

This plugs directly into your AI and gives it new abilities it didn't have before. Notion MCP Integration is a lightweight Model Context Protocol (MCP) server that seamlessly integrat. Once connected, just ask your AI to use it. It's completely free and works across most major AI apps. This one just landed in the catalog — worth trying while it's fresh.

Tips for getting started

1

Tap "Get" above, pick your AI app, and follow the steps. Most installs take under 30 seconds.

2

Heads up: this needs an API key to work. You'll get one from the service's website (usually free). The setup guide tells you exactly where.

3

Your data stays between you and your AI — nothing is shared with us or anyone else.

What's New

Version 1.0.06 days ago

Imported from GitHub

Ratings & Reviews

0.0

out of 5

0 ratings

No reviews yet. Be the first to share your experience.