Divide and Conquer MCP Server
@landicefu
Overview
What is Divide and Conquer MCP Server?
A Model Context Protocol (MCP) server that enables AI agents to break down complex tasks into manageable pieces using a structured JSON format. It is designed for AI agents facing context window limitations when working on multi-step or multi‑conversation tasks.
How to use Divide and Conquer MCP Server?
Add the server to your MCP configuration using npx -y @landicefu/divide-and-conquer-mcp-server, then invoke tools such as initialize_task, add_checklist_item, get_current_task_details, and get_checklist_summary via use_mcp_tool. The server stores task data locally in ~/.mcp_config/divide_and_conquer.json.
Key features of Divide and Conquer MCP Server
- Structured JSON format for task storage
- Checklist with completion status tracking
- Context preservation across conversations
- Progress monitoring and task ordering
- Task insertion at specific positions
- Metadata tracking (tags, priority, estimated time)
Use cases of Divide and Conquer MCP Server
- Complex software development tasks requiring multiple steps
- Project planning and management with structured checklists
- Research and analysis with organized findings and sources
FAQ from Divide and Conquer MCP Server
How does it differ from the Temp Notes MCP Server?
It is an evolution of Temp Notes that uses a structured JSON format instead of plain text, enabling checklists, context fields, metadata, and progress tracking.
Where is the task data stored?
On macOS/Linux at ~/.mcp_config/divide_and_conquer.json and on Windows at C:\Users\username\.mcp_config\divide_and_conquer.json. The file is created automatically on first write.
How does it help with context window limitations?
It selectively provides full context only for the current (first uncompleted) task, while other tasks are returned with limited fields, saving context window space.
Does it require any external services?
No, it runs locally as a Node.js process and requires no external APIs or databases.
What tools does it provide?
It offers 14 tools including initialize_task, add_checklist_item, mark_task_done, get_current_task_details, get_checklist_summary, and more for managing tasks, checklists, notes, resources, and metadata.
