Prerequisites
- Python 3.10 or higher
- A Notion account with an API integration set up
- Notion database with tasks (required properties: "Task", "Checkbox", "Deadline")
- Cursor IDE
Installation
-
Create a virtual environment and install dependencies:
uv venv source .venv/bin/activate # On Windows: .venv\\Scripts\\activate uv pip install -e . -
Set up
.envfile in the project root:NOTION_API_KEY=your_notion_api_key NOTION_DATABASE_ID=your_database_id NOTION_BASE_URL=https://api.notion.com/v1 NOTION_VERSION=2022-06-28
Setting Up Notion Integration
- Go to Notion Integrations
- Create a new integration and note the API key
- Share your database with the integration
- Get your database ID from the URL (it's the part after the workspace name and before the question mark)
Adding to Cursor Settings
- Open Cursor IDE
- Open Settings (⌘+shift+p), navigate to "MCP" tab
- Click "Add new global MCP server"
- Configure the Notion MCP with the following settings:
{
"mcpServers": {
"myNotionMcp":{
"command": "{path-to-venv-python}",
"args": ["-m", "notion_mcp"]
}
}
}
- Save the settings
Usage
Once configured, you can use the Notion MCP in Cursor by asking the AI assistant questions like:
- "What tasks should I complete this week?"
- "Show me my todos for today"
- "What are all my pending tasks?"
Troubleshooting
- Ensure your
.envfile is properly configured with the correct Notion API key and database ID - Check that your Notion database has the required properties: "Task", "Checkbox", and "Deadline"
- Make sure your Notion integration has been granted access to your database
- If you encounter any issues, try restarting Cursor
License
MIT
Recommend MCP Servers 💡
kagi-server
A Model Context Protocol server implementation for Kagi's API
fibery-mcp-server
This MCP (Model Context Protocol) server provides integration between Fibery and any LLM provider supporting the MCP protocol (e.g., Claude for Desktop), allowing you to interact with your Fibery workspace using natural language.
mcp-recon
mcp-recon bridges the gap between natural language and HTTP infrastructure analysis. It exposes reconnaissance tools through the Model Context Protocol (MCP), allowing you to perform web domain reconnaissance via any compatible AI interface, such as Claude Desktop.
teamretro-mcp-server
Model Context Protocol (MCP) server for TeamRetro integration
FileScopeMCP
Analyzes your codebase identifying important files based on dependency relationships. Generates diagrams and importance scores per file, helping AI assistants understand the codebase. Automatically parses popular programming languages such as Python, C, C++, Rust, Zig, Lua.
gget-mcp
Bioinformatic MCP server that wraps the most useful functions of the gget library