🚀 TaskMaster: Todoist MCP for Cursor AI
About
A lightweight Model Context Protocol (MCP) server that enables natural language interaction with your Todoist tasks directly from your IDE. Built with simplicity and maintainability in mind.
Explore
- Flexible Task Filtering: Filter tasks using Todoist's powerful filter syntax
- Filter by due date: today, tomorrow, overdue
- Filter by priority levels (1-4, where 1 is highest)
- Filter using complex query combinations
- Rich Task Formatting: Each task displays priority, due date, and other relevant information with clear icons
- Cursor AI Integration: Seamlessly use Todoist within your Cursor AI coding environment
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
🚀 TaskMaster: Todoist MCP for Cursor AICommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- Python 3.10 or higher
- Poetry (for dependency management)
- Todoist account and API token
To install TaskMaster for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @mingolladaniele/taskMaster-todoist-mcp --client claude
python server.py
filter_string
Advanced Todoist filter query string for complex filtering
priority
Optional priority level (1-4, where 1 is highest priority)
The server provides the following MCP tool:
Retrieves tasks with powerful filtering options.
Parameters:
- filter_string: Advanced Todoist filter query string for complex filtering
- priority: Optional priority level (1-4, where 1 is highest priority)
Example filter strings:
- "today" - Tasks due today
- "overdue" - Overdue tasks
- "Jan 3" - Tasks due on January 3rd
- "due before: May 5" - Tasks due before May 5th
- "due after: May 5" - Tasks due after May 5th
- "due before: +4 hours" - Tasks due within the next four hours and all overdue tasks
- "no date" - Tasks with no due date
- "5 days" or "next 5 days" - Tasks due in the next 5 days
- "recurring" - Tasks with a recurring date
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"\ud83d\ude80 taskmaster: todoist mcp for cursor ai": {
"taskMaster-todoist-mcp": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@mingolladaniele/taskMaster-todoist-mcp",
"--client",
"claude"
]
}
}
}
}McpServers
{
"taskMaster-todoist-mcp": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@mingolladaniele/taskMaster-todoist-mcp",
"--client",
"claude"
]
}
}A Model Context Protocol (MCP) server implementation for Todoist integration, specifically developed for Cursor AI. This server allows Cursor AI assistants to interact with your Todoist tasks directly from your coding environment.
Demo Video
Features
- Flexible Task Filtering: Filter tasks using Todoist's powerful filter syntax
- Filter by due date: today, tomorrow, overdue
- Filter by priority levels (1-4, where 1 is highest)
- Filter using complex query combinations
- Rich Task Formatting: Each task displays priority, due date, and other relevant information with clear icons
- Cursor AI Integration: Seamlessly use Todoist within your Cursor AI coding environment
Installation
Installing via Smithery
To install TaskMaster for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @mingolladaniele/taskMaster-todoist-mcp --client claude
Prerequisites
- Python 3.10 or higher
- Poetry (for dependency management)
- Todoist account and API token
Setup
1. Clone this repository:
git clone https://github.com/mingolladaniele/todoist-mcp.git
cd todoist-mcp
2. Install dependencies:
pip install -r requirements.txt
3. Set your Todoist API token as an environment variable:
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
