Integrates with Notion's API to manage personal todo list
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 is a personal project designed for a very specific use case: my simple Notion todo list that has just three properties:
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.
git clone https://github.com/yourusername/notion-mcp.git
cd notion-mcp
python -m venv .venv
source .venv/bin/activate # On Windows use: .venv\Scripts\activate
uv pip install -e .
Create a Notion integration:
Share your database with the integration:
Create a .env
file:
NOTION_API_KEY=your-api-key-here
NOTION_DATABASE_ID=your-database-id-here
{
"mcpServers": {
"notion-todo": {
"command": "/path/to/your/.venv/bin/python",
"args": ["-m", "notion_mcp"],
"cwd": "/path/to/notion-mcp"
}
}
}
The server can be run in two ways:
# From the project directory with virtual environment activated
python -m notion_mcp
claude_desktop_config.json
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.
Basic commands through Claude:
If you want to use this with a different database structure, you'll need to modify the server.py
file, particularly:
create_todo()
function to match your database propertiescall_tool()
to handle your data structurelist_tools()
if you want different optionsnotion_mcp/
├── pyproject.toml
├── README.md
├── .env # Not included in repo
└── src/
└── notion_mcp/
├── __init__.py
├── __main__.py
└── server.py # Main implementation
MIT License - Use at your own risk
Interact with the HireBase Job API to manage job listings and applications.
A comprehensive toolkit for text processing, formatting, and analysis.
Converts Markdown text into HTML compatible with WeChat official accounts using an external API key.
Perform queries and entity operations in your Fibery workspace.
Interact with task, doc, and project data in Dart, an AI-native project management tool
MCP server for seamless document format conversion using Pandoc, supporting Markdown, HTML, and plain text, with other formats like PDF, csv and docx in development.
Create professional PDF invoices using natural language.
Reads EndNote .enl libraries and exposes their contents through the MCP interface.
An MCP server that uses Google's Gemini 1.5 Pro to generate concise summaries of various content types.
Provides access to a specific user's memories from the Omi app.