Landicefu Divide And Conquer MCP Server

🚀 Divide and Conquer MCP Server

Divide and Conquer MCP Server is a tool that helps AI agents manage and track complex tasks. By breaking down large tasks into smaller ones and maintaining context information, the server enables agents to complete tasks across multiple conversations.

🚀 Quick Start

Divide and Conquer MCP Server is a tool designed to assist AI agents in managing and tracking complex tasks. It achieves this by breaking down large tasks into smaller, manageable ones and maintaining context information, allowing agents to complete tasks across multiple conversations.

✨ Features

• Break down large tasks into smaller, manageable ones.
• Track progress across multiple rounds of conversations.
• Maintain all task-related context information.
• Organize task decision-making and resource records.

💻 Usage Examples

1. Complex Software Development Tasks

When dealing with complex software development tasks, AI agents often struggle to complete all steps in a single conversation due to context window limitations. Divide and Conquer MCP Server allows agents to:

• Break down large tasks into smaller, manageable subtasks.
• Track progress across multiple conversations.
• Maintain important context information that would otherwise be lost.
• Organize a consistent sequence of tasks.
• Document decisions and resources.

2. Project Planning and Management

For project planning and management tasks, the server can:

• Create structured project plans that include subtasks.
• Track progress and completion status.
• Maintain context and requirement information.
• Document decisions and resources.
• Support collaboration across multiple conversations.

3. Research and Analysis

When conducting research and analysis, agents can:

• Break down research questions into specific research areas.
• Track progress and research results.
• Maintain context and background information.
• Document sources and resources.
• Organize structured presentations of research results.

📚 Documentation

JSON Format Structure

The server uses the following JSON format to store task information:

{
  "task_description": "A medium-grained detailed description of the ultimate goal of the entire task. The final outcome we hope to achieve.",
  
  "checklist": [
    {
      "done": false,
      "task": "A short but comprehensive task name",
      "detailed_description": "A longer description to explain what we hope to achieve through this task.",
      "context_and_plan": "Relevant information, documents to be read, details of other tasks, and a detailed plan for this task. This is usually a long text."
    }
  ],
  
  "context_for_all_tasks": "Information that each task in the task list should contain.",
  
  "metadata": {
    "created_at": "ISO timestamp",
    "updated_at": "ISO timestamp",
    "progress": {
      "completed": 0,
      "total": 1,
      "percentage": 0
    },
    "tags": ["tag1", "tag2"],
    "priority": "high|medium|low",
    "estimated_completion_time": "ISO timestamp"
  }
}

Configuration Storage Location

• File Path: %USERPROFILE%/.mcp_config/
• Default Settings:

{
  "server_port": 3000,
  "log_level": "info",
  "enable_logging": true
}

Feature Highlights

• Scalability: Supports task decomposition of any scale.
• Persistent Storage: Persists task data to local files.
• Logging: Provides progress tracking and error troubleshooting capabilities.
• Plugin Architecture: Supports custom extensions.

Installation Steps

1. Clone the source code:

git clone https://github.com/divide-and-conquer-mcp/server.git

2. Install dependencies:

npm install

3. Start the server:

npm start

Usage Examples

Create a New Project

1. Initialize the project directory:

mcp init my-project

2. Add a task:

mcp add-task --description "Implement the core algorithm" --priority high

3. View progress:

mcp list-tasks

Cross-Conversation Usage

⚠️ Important Note

• Data Storage: By default, task data is persisted to a local folder. Please ensure you have sufficient storage space.
• Network Connection: The server requires a stable network connection to synchronize progress. Any unsaved changes will be lost during a disconnection.
• Error Handling: Performance bottlenecks may occur under high load. It is recommended to use load balancing in a production environment.

📄 License

This software is licensed under the MIT License. The full LICENSE file can be found in the source code repository.