Todo

You run a TypeScript MCP server that gives AI agents powerful task management capabilities. It lets you create, organize, and track ordered todo lists with persistent storage, making complex projects easier to break down and manage.

How to use

You interact with the Todo MCP Server through an MCP client to manage tasks and monitor progress. Start by booting the local server, then use the client to create todo items, retrieve the next task to work on, update task details, mark tasks as completed, and query statistics. Tasks are automatically ordered by creation priority and persist across restarts, so your AI agents can pick up right where they left off. You can filter by pending or completed items and perform bulk operations when needed.

How to install

Prerequisites include Node.js 18.0.0 or higher and npm or yarn.

Step by step setup and run flow.

# Prerequisites check (example)
node -v
npm -v

# Install dependencies
npm install

# Build the project
npm run build

# Start the server locally (example; use the exact runtime path as shown in your setup)
node dist/index.js

Configuration

To use the server with Claude Desktop, configure the MCP server entry specific to your operating system. The following configurations start the server via a local node process and point to the built runtime.

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

Available tools

create_todo

Create a new todo item with a title and optional description.

get_todo

Retrieve a specific todo item by its ID.

get_todos

Get all todo items with optional status filtering.

get_next_todo

Retrieve the next priority todo item to work on.

update_todo

Update an existing todo item's title, description, or status.

complete_todo

Mark a todo item as completed.

delete_todo

Delete a todo item from the list.

get_todo_stats

Get statistics about all todo items, including totals and progress.

clear_all_todos

Remove all todo items from the server.