📝 Todo MCP Server

A simple Todo List MCP server built for learning!

What is this?

This is an MCP (Model Context Protocol) server that gives AI assistants (like Claude) the ability to manage a todo list for you.

Tools Included:

• add_todo - Add a new task

• list_todos - See all your tasks

• complete_todo - Mark a task as done ✅

• delete_todo - Remove a task 🗑️

Related MCP server: Firestore Todo List MCP Server

🚀 Quick Start

1. Install dependencies

cd todo-mcp
npm install

2. Build the project

npm run build

3. Test it works

node index.js

(Press Ctrl+C to stop - it will just wait for input)

🔌 Connect to Claude Desktop

Edit your Claude Desktop config file:

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

Add this to the file:

{
  "mcpServers": {
    "todo": {
      "command": "node",
      "args": ["/FULL/PATH/TO/todo-mcp/index.js"]
    }
  }
}

⚠️ Replace /FULL/PATH/TO/ with the actual path to your todo-mcp folder!

Then restart Claude Desktop.

🔌 Connect to Codebuff

Create or edit .codebuff/config.json in your project:

{
  "mcpServers": {
    "todo": {
      "command": "node",
      "args": ["/FULL/PATH/TO/todo-mcp/index.js"]
    }
  }
}

Or add to global config at ~/.codebuff/config.json.

Then restart Codebuff.

💡 How to Use

Once connected, just talk to Claude naturally:

• "Add 'buy groceries' to my todo list"

• "What's on my todo list?"

• "Mark todo #1 as complete"

• "Delete todo #2"

Claude will automatically use the right tools!

📚 Learning More

Look at index.ts - it's full of comments explaining every part!

Key concepts:

1. Tools = Actions the AI can take

2. inputSchema = What info each tool needs

3. Request Handlers = Code that runs when tools are used

⚠️ Note

Todos are stored in memory only - they disappear when the server restarts. This is intentional for learning! A real app would save to a file or database.