divide-and-conquer

The Divide and Conquer MCP Server provides a structured way for AI agents to break down complex tasks into manageable pieces using a JSON-driven format. It exposes a set of tools that let you create tasks, manage a checklist, update descriptions and context, add notes and resources, and reorder or remove checklist items. This enables persistent context and progress tracking across conversations, while preserving a clear task hierarchy and metadata such as tags and priority. Typical usage involves initializing a complex task, progressively filling out the checklist, and querying for current task details or a summary of progress to guide subsequent steps.

Prerequisites:

• Node.js and npm installed on your system
• Basic knowledge of your MCP configuration format

Option 1: Using npx (Recommended)

1. Add the server to your MCP configuration:

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

Option 2: Install from source

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. Add the server to your MCP configuration (example):

{
  "mcpServers": {
    "divide-and-conquer": {
      "command": "node",
      "args": ["/path/to/divide-and-conquer-mcp-server/build/index.js"],
      "disabled": false
    }
  }
}

Notes and tips:

• If you choose the npx approach, the server will be fetched on demand from the npm registry. Ensure you have network access when starting the MCP.
• The toolset supports task initialization, dynamic checklist management, and detailed current-task retrieval. Use get_current_task_details to fetch the current task with full context and other tasks with limited fields to optimize context window usage.
• When updating context or metadata, consider the impact on subsequent tool outputs and ensure that context_for_all_tasks remains relevant across iterations.
• For large task trees, keep metadata and notes concise to avoid excessive memory usage in long-running conversations.