Divide and Conquer MCP Server

@landicefu

リポジトリ

基本情報

カテゴリ

その他

ライセンス

MIT

トランスポート

stdio

作者

landicefu

Divide and Conquer MCP Server について

概要はまだありません

#divide-and-conquer#mcp-server #task-management

Divide and Conquer MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

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

Divide and Conquer MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

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

よくある質問

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.

「その他」の他のコンテンツ

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Reactive Resume

amruthpillai

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

39.5K

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

MaxKB

1Panel-dev

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

22.0K

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context