todoist-mcp

todoist-mcp

A Python-based MCP server for Todoist that enables comprehensive task management, including reading, creating, and updating tasks, projects, and comments. It features a specialized rescheduling tool designed to safely preserve reminders and recurring patterns during date changes.

Category
Visit Server

README

todoist-mcp

A Python MCP server for Todoist that provides safe task rescheduling.

The official Todoist MCP server's task-update tool silently drops reminders and flattens recurring tasks when changing due dates. This server fixes that by routing all date changes through a custom reschedule_task tool that preserves both.

Tools

Read

Tool Description
get_task Fetch a single task by ID
find_tasks Filter tasks by Todoist query string, project, or label
find_tasks_by_date Tasks due on or between dates
get_projects List all projects
get_sections List sections in a project
get_comments Get comments on a task
get_overview Overdue + today summary, or all tasks in a project

Write

Tool Description
add_task Create a task (supports due_string, priority, labels)
update_task Update content, description, priority, or labels — no due-date params
complete_task Mark a task done
add_project Create a project
add_section Create a section
add_comment Add a comment to a task

Rescheduling

Tool Description
reschedule_task Move a task to a new date, safely preserving recurring patterns and reminders

update_task deliberately has no due-date parameters in its schema. The model cannot use it to change dates even if instructed to — reschedule_task is the only path.

Setup

Prerequisites

  • uv
  • A Todoist API token (find it at Todoist → Settings → Integrations → API token)

Install

git clone https://github.com/kpanko/todoist-mcp
cd todoist-mcp
cp .env.example .env
# edit .env and add your token
uv sync

Configure Claude Code

Add to your MCP config (.claude/mcp_config.json or Claude Desktop's claude_desktop_config.json):

{
  "mcpServers": {
    "todoist": {
      "command": "uv",
      "args": [
        "--project", "/path/to/todoist-mcp",
        "run", "todoist-mcp"
      ]
    }
  }
}

The server reads TODOIST_API_TOKEN from the environment or from a .env file in the project root. No OAuth or browser auth required — works in headless background services.

Dependencies

Why not use the official server?

The official server at https://ai.todoist.net/mcp requires OAuth (browser flow), making it unsuitable for background services. It also exposes an update_task tool that accepts due-date parameters, which the Todoist REST API handles by dropping reminders and converting recurring tasks to one-time tasks.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured