TaskMaster provides seamless integration between Cursor AI and Todoist, allowing you to interact with your tasks directly from your coding environment. Using the Model Context Protocol (MCP), this server enables Cursor AI assistants to fetch and display your Todoist tasks with rich formatting and powerful filtering capabilities.
The fastest way to install TaskMaster is through Smithery:
npx -y @smithery/cli install @mingolladaniele/taskMaster-todoist-mcp --client claude
Before installing, ensure you have:
Clone the repository:
git clone https://github.com/mingolladaniele/todoist-mcp.git
cd todoist-mcp
Install dependencies:
pip install -r requirements.txt
Set your Todoist API token as an environment variable:
# Linux/macOS
export TODOIST_API_TOKEN="your-api-token-here"
# Windows
set TODOIST_API_TOKEN="your-api-token-here"
You can find your API token in Todoist settings → Integrations → Developer.
Launch the server with:
python server.py
To use TaskMaster with Cursor AI, create or edit the MCP configuration file:
Windows: C:\Users\<username>\.cursor\mcp.json
{
"mcpServers": {
"todoist-mcp": {
"command": "C:/Users/<username>/path/to/todoist-mcp/.venv/Scripts/python.exe",
"args": [
"C:/Users/<username>/path/to/todoist-mcp/server.py"
],
"env": {
"TODOIST_API_TOKEN": "your-api-token-here"
}
}
}
}
Replace <username>
and paths with your actual username and the correct paths to your installation.
After configuration, go to Cursor Settings → MCP and verify the server is running (indicated by a green dot).
TaskMaster provides a powerful get_tasks_tool
with flexible filtering options:
By date:
"today"
- Tasks due today"tomorrow"
- Tasks due tomorrow"overdue"
- Overdue tasks"Jan 3"
- Tasks due on January 3rd"5 days"
or "next 5 days"
- Tasks due in the next 5 daysBy timeframe:
"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 tasksSpecial filters:
"no date"
- Tasks with no due date"recurring"
- Tasks with a recurring dateBy priority:
Each task displayed will include priority level, due date, and other relevant information with clear formatting.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.