MCP Todo List App

MCP Todo List App

What is MCP Todo List App about?

A todo list manager that provides full CRUD functionality for tasks and exposes MCP‑compliant tools, enabling AI assistants and chatbots to interact with the task data programmatically.

How to use MCP Todo List App?

1. Add the server entry to claude_desktop_config.json:

{
  "mcpServers": {
    "todos": {
      "command": "npx",
      "args": ["-y", "todos-mcp"]
    }
  }
}

2. Install dependencies and start the development server:

git clone https://github.com/tomelliot/todos-mcp.git
cd mcp-todo-app
npm install   # or yarn install
npm run dev   # or yarn dev

3. Interact with the exposed MCP tools (e.g., Add-Todo, List-All-Todos) from an AI assistant or via HTTP calls as defined by the MCP specification.

Key Features of MCP Todo List App

• Full task lifecycle management (create, read, update, delete)
• Local storage eliminates the need for external SaaS accounts
• MCP‑compliant API with tools such as Get-Todo, Add-Todo, Mark-Todo-Done, and various list filters
• Simple Node.js setup using npx for quick execution

Use Cases of MCP Todo List App

• Personal productivity: Quickly add, complete, and view tasks via voice or chat interfaces.
• AI‑driven assistants: Enable bots to schedule, query, and modify a user's todo list using natural language.
• Development demos: Showcase MCP integration in tutorials or proof‑of‑concept projects.
• Automation scripts: Combine with other MCP services to build complex workflows (e.g., reminders, calendar sync).

FAQ from the MCP Todo List App

Q: Do I need an internet connection? A: No. All data is stored locally in the browser or filesystem, so the app works offline.

Q: Can I use a different package manager? A: Yes. While the config uses npx, you can run the server with npm start or yarn dev after installation.

Q: Is there a way to persist data across sessions? A: The app uses local storage by default, which retains tasks between browser sessions.

Q: How do I add custom MCP tools? A: Extend the server’s tool registry in the source code and follow the MCP specification for tool definitions.

Q: Is the project open source? A: Yes, it is licensed under the GPL license.

MCP Todo List App

A todo list application implementing Model Context Protocol (MCP), enabling seamless interaction with AI assistants and chatbots. This application is a practical todo list manager and a demonstration of MCP integration.

Features

• ✨ Full todo list functionality (create, read, update, delete tasks)
• 🤖 MCP-compliant API for AI assistant integration
• 🏠 Local storage (no SaaS account required)

What is MCP?

The Model Context Protocol (MCP) is a standardized interface that allows AI models and chatbots to interact with applications in a consistent and predictable way. By implementing MCP, this todo list app can be seamlessly controlled by AI assistants, enabling natural language interactions for task management.

Getting Started

1. Open Claude config file
2. Add the todos server to your claude_desktop_config.json (usually found at ~/Library/Application Support/Claude/claude_desktop_config.json on MacOS)

{
  "mcpServers": {
    // ...
    "todos": {
      "command": "npx",
      "args": ["-y", "todos-mcp"]
    }
    // ...
  }
}

Development

Prerequisites

• Node.js (v16 or higher)
• npm or yarn

Installation

1. Clone the repository:

git clone https://github.com/tomelliot/todos-mcp.git
cd mcp-todo-app

2. Install dependencies:

npm install
# or
yarn install

3. Start the development server:

npm run dev
# or
yarn dev

MCP Integration

This todo list app exposes the following MCP tools:

• Get-Todo: Get a specific todo by ID
• List-All-Todos: List all todos
• List-Completed-Todos: List all completed todos
• List-Pending-Todos: List all pending todos
• Add-Todo: Add a todo
• Mark-Todo-Done: Mark a todo item as completed
• List-Due-Today: List all pending todos that are due today or overdue
• List-Due-This-Week: List all pending todos that are due this week or earlier
• Update-Todo: Update a todo's description and/or due date

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the GPL License - see the LICENSE file for details.

Acknowledgments

• Built with modern web technologies
• Implements MCP specification for AI integration
• Inspired by the need for AI-friendly applications