Divide and Conquer

Divide and Conquer MCP Server lets AI agents break down complex tasks into a structured JSON format, track progress with checklists, preserve task context, and manage tasks in a clear sequence so conversations stay organized and coordinated.

How to use

You interact with the Divide and Conquer MCP Server through an MCP client to create and manage tasks, add checklists, store context, and retrieve task details. Start by initializing a new task with a description and optional context. Then incrementally add checklist items, update descriptions, attach notes or resources, and set metadata like priority or estimated completion time. You can request a summary of the checklist or fetch details for the current task to keep the flow focused on the next actionable step.

Typical usage patterns include:

• Create a new task with a clear description and shared context for all tasks.
• Build a checklist in order, adding detailed descriptions and planning notes for each item.
• Update task context as you learn more, keeping relevant information accessible to all future steps.
• Retrieve a compact checklist summary to see what’s done and what remains.
• Fetch the current task details to work on the first uncompleted item with full context.

How to install

Prerequisites: Node.js installed on your machine. You should also have npm and/or npx available in your environment.

Option 1: Install via npx (recommended for quick start)

{
  "mcpServers": {
    "divide_and_conquer": {
      "command": "npx",
      "args": ["-y", "@landicefu/divide-and-conquer-mcp-server"],
      "disabled": false
    }
  }
}

Option 2: Install from source (build and run locally)

# 1) Clone the repository
git clone https://github.com/landicefu/divide-and-conquer-mcp-server.git
cd divide-and-conquer-mcp-server

# 2) Install dependencies
npm install

# 3) Build the server
npm run build

# 4) Configure the MCP server to run the built file
# (example path; replace with your actual path)
{
  "mcpServers": {
    "divide_and_conquer": {
      "command": "node",
      "args": ["/path/to/divide-and-conquer-mcp-server/build/index.js"],
      "disabled": false
    }
  }
}

Configuration storage

Task data is stored in a local JSON file. The file path varies by operating system and is created automatically when you first initialize a task. If the file or directory doesn’t exist when you read or write, the server creates the necessary structure and returns appropriate data or errors.

Security and notes

Keep your task data local or in a controlled environment. Treat task metadata, notes, and resources as potentially sensitive information and limit access to authorized clients and users.

Troubleshooting

If you encounter issues starting the server, verify Node and npm/npx are installed and that the configured path to the built server is correct. Check permissions for the configuration file location and ensure you have network access when using npm/npx-based startup.

Tools and endpoints overview

The server provides a set of tools to manage tasks, each with its own purpose for building, updating, and querying task data. Examples include creating a task, updating descriptions, adding checklist items, marking items as done, reordering items, and retrieving summaries and current task details.

Metadata and configuration at a glance

Language: JavaScript
Package managers: npm, npx
Primary MCP server name: divide_and_conquer
Environment variables: none shown in setup
Tools: initialize_task, update_task_description, update_context, add_checklist_item, update_checklist_item, mark_task_done, mark_task_undone, remove_checklist_item, reorder_checklist_item, add_note, add_resource, update_metadata, clear_task, get_checklist_summary, get_current_task_details

Available tools

initialize_task

Creates a new task with a specified description, optional initial checklist, and optional context for all tasks.

update_task_description

Updates the main task description to reflect new goals or scope.

update_context

Updates the contextual information shared across all tasks in the current workflow.

add_checklist_item

Adds a new item to the current task's checklist with a description and optional context.

update_checklist_item

Updates an existing checklist item with new details or status.

mark_task_done

Marks a specific checklist item as completed.

mark_task_undone

Marks a specific checklist item as not completed.

remove_checklist_item

Removes a checklist item from the current task.

reorder_checklist_item

Moves a checklist item to a new position within the checklist.

add_note

Adds a note to record additional observations or decisions.

add_resource

Adds a reference resource to the task for later review.

update_metadata

Updates metadata such as tags, priority, and estimated completion time.

clear_task

Clears the current task data to start fresh.

get_checklist_summary

Returns a summary of the checklist with completion status; context is excluded for brevity.

get_current_task_details

Retrieves details of the current task (first uncompleted) with full context and a summarized view of other tasks.