Plan_mcp_service

Name: Plan_mcp_service
Author: Danson-dan

@Danson-dan

代码仓库

关于 Plan_mcp_service

Plan Manager MCP Service

基本信息

分类

其他

传输方式

stdio

发布者

Danson-dan

提交者

Danson

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "DEXIUbyxuu5XNTb_Fm_fM": {
      "name": "通用计划管理",
      "description": "",
      "baseUrl": "",
      "command": "uv",
      "args": [
        "--directory",
        "/Users/danson/Desktop/test-code/MCP_Server/plan_server_mcp",
        "run",
        "main.py"
      ],
      "env": {},
      "isActive": true,
      "type": "stdio",
      "registryUrl": ""
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Plan_mcp_service?

Plan_mcp_service is a universal plan management service for LLMs, built with the Model Context Protocol (MCP). It allows AI agents to create, manage, and track any kind of plan—such as travel itineraries, study schedules, or habit challenges—using a flexible, tree-based task structure.

How to use Plan_mcp_service?

—

Key features of Plan_mcp_service

Tree-based plan structure for flexible task management.
Supports any type of plan (travel, study, habits, etc.).
Built on the Model Context Protocol (MCP).
Allows AI agents to create, manage, and track plans.

Use cases of Plan_mcp_service

AI agents organizing travel itineraries with subtasks.
Managing study schedules and assignments for students.
Tracking 21-day habit challenges with daily tasks.
General-purpose plan creation and tracking by LLMs.

FAQ from Plan_mcp_service

What types of plans does Plan_mcp_service support?

It supports any kind of plan—from travel itineraries and study schedules to 21-day habit challenges.

What is the underlying technology?

It is built with the Model Context Protocol (MCP).

Does it require any specific runtime or dependencies?

—

Where does plan data live?

—

What transport or authentication does it use?

—

其他分类下的更多 MCP 服务器

Codelf

unbug

A search tool helps dev to solve the naming things problem.

14.2K

Core Philosophy: Connect, Unify, Respond

mindsdb

Delegate anything. It comes back done.

39.4K

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K