Task Manager MCP server

This MCP TaskManager serves as a Model Context Protocol server specifically designed for task management. It enables Claude Desktop or any MCP client to manage and execute tasks in a queue-based system, providing an organized way to handle multiple tasks sequentially.

Installation and Setup

Prerequisites

• Node.js 18 or higher (install via brew install node)
• Claude Desktop (download from https://claude.ai/desktop)

Configuration

To set up the TaskManager with Claude Desktop:

1. Locate your Claude Desktop configuration file at: ~/Library/Application Support/Claude/claude_desktop_config.json

   You can also find this through Claude Desktop:

   • Open Claude Desktop
   • Click "Claude" in the Mac menu bar
   • Select "Settings"
   • Click "Developer"

2. Add the TaskManager to your configuration by adding the following to your JSON file:

{
  "tools": {
    "taskmanager": {
      "command": "npx",
      "args": ["-y", "@kazuph/mcp-taskmanager"]
    }
  }
}

Using the TaskManager

The TaskManager operates in two main phases:

Planning Phase

In this phase, you provide a list of tasks that need to be executed:

{
  action: "plan",
  tasks: ["Task 1", "Task 2", "Task 3"]
}

This will:

• Store your tasks in an internal queue
• Return an execution plan with an overview of tasks
• Include task IDs and the current queue status

Execution Phase

When you're ready to start executing tasks:

{
  action: "execute",
  getNext: true
}

This will:

• Return the next task from the queue
• Prepare it for execution

Completing Tasks

After finishing a task, mark it as complete:

{
  action: "complete",
  taskId: "task-123"
}

This will:

• Remove the completed task from the queue
• Prepare the system for the next task

Parameter Reference

The TaskManager accepts the following parameters:

• action: Specifies the operation mode

  • "plan" - Set up tasks
  • "execute" - Run tasks
  • "complete" - Mark tasks as finished

• tasks: Array of task strings (required for "plan" action)

• taskId: Task identifier (required for "complete" action)

• getNext: Boolean flag to request the next task (for "execute" action)

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

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

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.