Todo MCP Server

Todo MCP Server

A TypeScript-based server that enables AI agents to create, prioritize, and manage ordered task lists for complex projects. It provides tools for task tracking, status filtering, and progress statistics with persistent storage.

Category
访问服务器

README

Todo MCP Server

A TypeScript MCP (Model Context Protocol) server that provides AI agents with powerful task management capabilities. This server enables Claude and other AI assistants to create, organize, and manage ordered task lists - perfect for breaking down complex projects into manageable, prioritized steps.

Installation

Prerequisites

  • Node.js 18.0.0 or higher
  • npm or yarn

Setup

  1. Clone this repository
  2. Install dependencies:
    npm install
    
  3. Build the project:
    npm run build
    

Claude Desktop Configuration

To use this server with Claude Desktop, add the following to your Claude Desktop config file:

Windows

Edit %APPDATA%\Claude\claude_desktop_config.json:

{
  "mcpServers": {
    "todo": {
      "command": "node",
      "args": ["path/to/todo-mcp-server/dist/index.js"]
    }
  }
}

macOS

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "todo": {
      "command": "node",
      "args": ["/path/to/todo-mcp-server/dist/index.js"]
    }
  }
}

Linux

Edit ~/.config/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "todo": {
      "command": "node",
      "args": ["/path/to/todo-mcp-server/dist/index.js"]
    }
  }
}

Note: Replace path/to/todo-mcp-server with the actual path to your installed server.

Features

Core Task Management

  • Create Todo Items - Add new tasks with titles and optional descriptions
  • Get Next Task - Retrieve the next priority task to work on
  • Update Tasks - Modify task titles, descriptions, or status
  • Complete Tasks - Mark tasks as completed
  • Delete Tasks - Remove tasks from the list
  • Task Statistics - Get overview of pending and completed tasks

Advanced Organization

  • Ordered Task Lists - Tasks are automatically ordered by creation priority
  • Status Filtering - Filter tasks by pending or completed status
  • Bulk Operations - Clear all tasks when needed
  • Persistent Storage - Tasks persist across server restarts

MCP Resources

The server exposes several resources for easy data access:

  • todo://todos - All todo items
  • todo://todos/pending - Only pending tasks
  • todo://todos/completed - Only completed tasks
  • todo://todos/next - The next task to work on

Showcase

image image image

Perfect for Complex Task Breakdown

This server excels at helping AI agents break down complex projects into manageable steps:

Example: "Build a Web Application"

Agent: "I need to build a web application with user authentication"

Using the todo server, the agent can:
1. Create main tasks: "Set up project structure", "Implement authentication", "Build UI"
2. Break down each task into subtasks
3. Work through them systematically using get_next_todo
4. Track progress with completion status
5. Get statistics on overall progress

Example Workflow

// Agent creates ordered tasks
create_todo("Set up project structure")
create_todo("Install dependencies") 
create_todo("Create user authentication system")
create_todo("Build login/register components")
create_todo("Implement protected routes")
create_todo("Add error handling")
create_todo("Write tests")
create_todo("Deploy application")

// Agent works through tasks systematically
get_next_todo() // Returns "Set up project structure"
complete_todo("task-id-1")
get_next_todo() // Returns "Install dependencies"

Usage Examples

Once configured, you can interact with the todo server through Claude Desktop:

Creating and Managing Tasks

You: "I need to plan a website redesign project"

Claude: I'll help you break this down into manageable tasks using the todo system.

[Claude creates tasks like:]
- Research current design trends
- Analyze user feedback
- Create wireframes
- Design new layout
- Implement responsive design
- Test across devices
- Launch new design

Working Through Tasks

You: "What should I work on next?"

Claude: [Uses get_next_todo] 
Let me check your next priority task...

Your next task is: "Research current design trends"
Description: "Look into modern web design patterns, color schemes, and user experience best practices"

Tracking Progress

You: "How am I doing on my project?"

Claude: [Uses get_todo_stats]
Here's your current progress:
- Total tasks: 15
- Completed: 8
- Pending: 7

You're making great progress! 53% complete.

Available Tools

Tool Description
create_todo Create a new todo item with title and optional description
get_todo Retrieve a specific todo item by ID
get_todos Get all todos with optional status filtering
get_next_todo Get the next priority todo item
update_todo Update an existing todo item
complete_todo Mark a todo item as completed
delete_todo Delete a todo item
get_todo_stats Get statistics about todo items
clear_all_todos Clear all todo items

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