Todoist MCP Server

Todoist MCP Server

An MCP server that integrates with the Todoist REST API v2 to enable AI assistants to manage tasks, projects, sections, comments, and labels. It supports comprehensive operations including batch task creation, history tracking for completed tasks, and organized project management.

Category
访问服务器

README

Todoist MCP Server

A Model Context Protocol (MCP) server that provides integration with the Todoist REST API v2, enabling AI assistants to manage tasks, projects, sections, comments, and labels.

Note: I used this project to test out Factory.ai -- use with caution.

Features

  • Task Management: Create, update, complete, delete, move, and search tasks
  • Batch Operations: Create multiple tasks at once
  • Project Management: Create, update, and delete projects
  • Section Management: Organize tasks within project sections
  • Comments: Add rich text comments with markdown support and optional prefixes ([Research], [Prompt], [Context], etc.)
  • Labels: Manage personal labels
  • Completed Tasks: Access completed task history via Sync API
  • Rate Limiting: Built-in handling for Todoist's 450 requests/15 min limit with exponential backoff

Installation

npm install
npm run build

Configuration

  1. Get your Todoist API token from Todoist Settings > Integrations > Developer

  2. Add to your MCP client configuration (e.g., Claude Desktop):

{
  "mcpServers": {
    "todoist": {
      "command": "node",
      "args": ["/path/to/todoist-mcp/dist/index.js"],
      "env": {
        "TODOIST_API_TOKEN": "your-api-token"
      }
    }
  }
}

Important: Never commit your API token to version control. Store it securely in your local MCP configuration.

Available Tools

Task Operations

  • todoist_list_tasks - List active tasks with filters
  • todoist_get_task - Get a single task
  • todoist_create_task - Create a new task
  • todoist_update_task - Update an existing task
  • todoist_complete_task - Mark task as completed
  • todoist_reopen_task - Reopen a completed task
  • todoist_delete_task - Delete a task
  • todoist_move_task - Move task to different project/section
  • todoist_search_tasks - Search tasks by content
  • todoist_create_tasks_batch - Create multiple tasks at once

Project Operations

  • todoist_list_projects - List all projects
  • todoist_get_project - Get a project
  • todoist_create_project - Create a new project
  • todoist_update_project - Update a project
  • todoist_delete_project - Delete a project

Section Operations

  • todoist_list_sections - List all sections
  • todoist_get_section - Get a section
  • todoist_create_section - Create a new section
  • todoist_update_section - Update a section
  • todoist_delete_section - Delete a section

Comment Operations

  • todoist_list_comments - List comments for task/project
  • todoist_get_comment - Get a comment
  • todoist_create_comment - Create a comment with optional prefix
  • todoist_update_comment - Update a comment
  • todoist_delete_comment - Delete a comment
  • todoist_add_research_comment - Add [Research] prefixed comment
  • todoist_add_context_comment - Add [Context] prefixed comment

Label Operations

  • todoist_list_labels - List all labels
  • todoist_create_label - Create a new label
  • todoist_update_label - Update a label
  • todoist_delete_label - Delete a label

Completed Tasks

  • todoist_list_completed_tasks - List completed tasks
  • todoist_get_completed_stats - Get completion statistics

Response Format

All tools return a structured response:

{
  success: boolean;
  data?: any;        // Present on success
  error?: {          // Present on failure
    code: string;
    message: string;
    details?: any;
  };
}

Development

npm run dev    # Watch mode for development
npm run build  # Build for production
npm run typecheck  # Type check without emitting

License

ISC

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