Todoist MCP Server

Todoist MCP Server

A comprehensive Model Context Protocol (MCP) server for the Todoist API. Provides full access to tasks, projects, labels, sections, and comments with support for all task properties including priorities, due dates, labels, subtasks, and more.

Category
访问服务器

README

Todoist MCP Server

A comprehensive Model Context Protocol (MCP) server for the Todoist API. Provides full access to tasks, projects, labels, sections, and comments with support for all task properties including priorities, due dates, labels, subtasks, and more.

Features

  • Complete Task Management: Create, read, update, delete, complete, and reopen tasks
  • Full Task Properties Support: Content, description, due dates (natural language or specific), priority (1-4), labels, duration estimates, subtasks, assignees, and more
  • Project Management: Create and manage projects with colors, hierarchies, and view styles
  • Label Management: Create and organize labels for cross-project task categorization
  • Section Management: Organize tasks within projects using sections
  • Comment Management: Add and manage comments on tasks and projects
  • Rate Limiting: Built-in rate limit handling (450 requests per 15 minutes)
  • Error Handling: Comprehensive error handling with meaningful error messages

Installation

Prerequisites

  • Node.js (v18 or higher)
  • npm
  • A Todoist account with API token

Get Your Todoist API Token

  1. Log in to your Todoist account
  2. Go to Settings → Integrations → Developer
  3. Copy your API token
  4. Set it as an environment variable: TODOIST_API_TOKEN

Install the Server

# Clone or download this repository
cd todoist-mcp

# Install dependencies
npm install

# Build the project
npm run build

Configuration

For Claude Desktop

Add this to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "todoist": {
      "command": "node",
      "args": [
        "E:\\my drive\\programs and files\\dev\\todoist MCP\\build\\index.js"
      ],
      "env": {
        "TODOIST_API_TOKEN": "your_api_token_here"
      }
    }
  }
}

Replace the path with your actual installation path and add your Todoist API token.

For Other MCP Clients

Set the TODOIST_API_TOKEN environment variable and run:

node build/index.js

Available Tools

Task Management

list_tasks

Get all active tasks with optional filtering.

Parameters:

  • project_id (optional): Filter by project
  • section_id (optional): Filter by section
  • label (optional): Filter by label name
  • filter (optional): Custom filter string (e.g., 'today', 'p1', 'overdue')
  • lang (optional): Language code for filter parsing

Example:

{
  "filter": "today",
  "project_id": "2203306141"
}

get_task

Get a single task by ID with all properties.

Parameters:

  • task_id (required): Task ID

create_task

Create a new task with comprehensive properties.

Parameters:

  • content (required): Task title
  • description (optional): Task description
  • project_id (optional): Project ID
  • section_id (optional): Section ID
  • parent_id (optional): Parent task ID for subtasks
  • priority (optional): 1-4, where 4 is urgent
  • labels (optional): Array of label names
  • due_string (optional): Natural language due date (e.g., "tomorrow at 14:00")
  • due_date (optional): YYYY-MM-DD format
  • due_datetime (optional): RFC3339 format
  • due_lang (optional): Language for parsing due_string
  • assignee_id (optional): User ID to assign
  • duration (optional): Duration amount
  • duration_unit (optional): "minute" or "day"

Example:

{
  "content": "Buy groceries",
  "description": "Milk, eggs, bread",
  "priority": 3,
  "labels": ["shopping", "urgent"],
  "due_string": "tomorrow at 14:00"
}

update_task

Update an existing task.

Parameters:

  • task_id (required): Task ID
  • All other parameters from create_task (optional)

complete_task

Mark a task as complete. Recurring tasks move to next occurrence.

Parameters:

  • task_id (required): Task ID

reopen_task

Reopen a completed task.

Parameters:

  • task_id (required): Task ID

delete_task

Permanently delete a task.

Parameters:

  • task_id (required): Task ID

Project Management

list_projects

Get all projects.

get_project

Get a single project by ID.

Parameters:

  • project_id (required): Project ID

create_project

Create a new project.

Parameters:

  • name (required): Project name
  • parent_id (optional): Parent project ID for nested projects
  • color (optional): Color name (e.g., "blue", "red")
  • is_favorite (optional): Boolean
  • view_style (optional): "list" or "board"

update_project

Update an existing project.

Parameters:

  • project_id (required): Project ID
  • All other parameters from create_project (optional)

delete_project

Permanently delete a project and all its tasks.

Parameters:

  • project_id (required): Project ID

Label Management

list_labels

Get all labels.

get_label

Get a single label by ID.

Parameters:

  • label_id (required): Label ID

create_label

Create a new label.

Parameters:

  • name (required): Label name
  • color (optional): Color name
  • order (optional): Position in list
  • is_favorite (optional): Boolean

update_label

Update an existing label.

Parameters:

  • label_id (required): Label ID
  • All other parameters from create_label (optional)

delete_label

Permanently delete a label.

Parameters:

  • label_id (required): Label ID

Section Management

list_sections

Get all sections, optionally filtered by project.

Parameters:

  • project_id (optional): Project ID

get_section

Get a single section by ID.

Parameters:

  • section_id (required): Section ID

create_section

Create a new section.

Parameters:

  • name (required): Section name
  • project_id (required): Project ID
  • order (optional): Position in project

update_section

Update an existing section.

Parameters:

  • section_id (required): Section ID
  • name (required): New section name

delete_section

Delete a section (tasks are not deleted).

Parameters:

  • section_id (required): Section ID

Comment Management

list_comments

Get comments for a task or project.

Parameters:

  • task_id (optional): Task ID
  • project_id (optional): Project ID

get_comment

Get a single comment by ID.

Parameters:

  • comment_id (required): Comment ID

create_comment

Create a new comment.

Parameters:

  • content (required): Comment text
  • task_id (optional): Task ID
  • project_id (optional): Project ID
  • attachment (optional): File attachment object

update_comment

Update an existing comment.

Parameters:

  • comment_id (required): Comment ID
  • content (required): Updated comment text

delete_comment

Permanently delete a comment.

Parameters:

  • comment_id (required): Comment ID

Development

# Watch mode for development
npm run watch

# Build
npm run build

Rate Limits

The Todoist API has the following rate limits:

  • 450 requests per 15 minutes per user

The server automatically tracks requests and throws an error if the limit is exceeded.

Error Handling

All tools provide meaningful error messages when operations fail. Common errors include:

  • Missing or invalid API token
  • Rate limit exceeded
  • Invalid task/project/label IDs
  • Invalid parameter values

License

MIT

Contributing

Contributions are welcome! Please feel free to submit issues or pull requests.

API Version

This server uses Todoist REST API v2.

Acknowledgments

Built using the Model Context Protocol SDK and the Todoist REST API.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选