Planner MCP Server

Planner MCP Server

A server for creating and managing plans with steps, enabling users to break down complex tasks into manageable steps and track progress.

Category
访问服务器

README

Planner MCP Server

A Model Context Protocol server for creating and managing plans with steps. This server helps break down complex tasks into manageable steps and track their progress.

Features

Plans

  • Create and manage plans with descriptive names and detailed descriptions
  • Each plan contains ordered steps with clear completion conditions
  • Track plan progress through active steps
  • Plans maintain a history of completed and failed steps
  • Paginated listing of plans (10 per page), ordered by creation date (newest first)
  • Automatic tracking of creation dates with user-friendly formatting (e.g., "just now", "2 hours ago", "yesterday")

Steps

  • Create specific, measurable steps with clear completion conditions
  • Track step status (in_progress, completed, failed)
  • Automatic step progression on completion
  • Ability to handle step failures with alternative approaches

Tools

create_plan

Creates a new plan with a descriptive name and description.

  • Parameters:
    • name: string - Name of the plan
    • description: string - Detailed description of the plan and its objectives
  • Returns: Plan details including ID, name, description, and status

list_plans

Lists all available plans with their current status and active steps, ordered by creation date (newest first). Results are paginated with 10 plans per page. Returns a helpful message if no plans exist.

  • Parameters:
    • page: number (optional) - Page number to retrieve (1-based, defaults to 1)
  • Returns:
    • Array of plans with their details (or a message if no plans exist)
    • Current page number
    • Total number of pages
    • Whether there is a next page available

create_step

Adds a new step to a plan. Steps should be specific, measurable actions that contribute to the plan's completion.

  • Parameters:
    • plan_id: string - ID of the plan
    • description: string - Step description
    • completion_condition: string - Clear condition that must be met to consider this step complete
  • Returns: Created step details

get_active_step

Gets the current active step of a plan.

  • Parameters:
    • plan_id: string - ID of the plan
  • Returns: Active step details if exists

complete_step

Marks a step as completed and automatically advances to the next step.

  • Parameters:
    • step_id: string - ID of the step to complete
  • Returns: Next step details if available

fail_step

Marks the current active step as failed and creates a new alternative step.

  • Parameters:
    • step_id: string - ID of the active step to mark as failed
    • new_step_description: string - Description of the new alternative step
    • new_step_completion_condition: string - Completion condition for the new alternative step
  • Returns: Failed step ID and new step details
  • Note: Can only fail the current active step

list_steps

Lists all steps in a plan in their execution order.

  • Parameters:
    • plan_id: string - ID of the plan
  • Returns: Array of steps with their details

export_plan

Exports a plan to markdown format including all steps and their status. The output will be formatted as a markdown document suitable for sharing or documentation purposes.

  • Parameters:
    • plan_id: string - ID of the plan to export
  • Returns:
    • Object containing:
      • markdown: string - Markdown formatted content of the exported plan
      • Includes plan details, status, and all steps with their descriptions and completion conditions
      • Steps are ordered by their execution sequence

Database Schema

Plans Table

  • id: TEXT PRIMARY KEY
  • name: TEXT NOT NULL
  • description: TEXT NOT NULL
  • created_at: DATETIME
  • active_step_id: TEXT

Steps Table

  • id: TEXT PRIMARY KEY
  • plan_id: TEXT NOT NULL
  • description: TEXT NOT NULL
  • completion_condition: TEXT NOT NULL
  • status: TEXT (in_progress, completed, failed)
  • step_order: INTEGER NOT NULL
  • created_at: DATETIME
  • FOREIGN KEY(plan_id) REFERENCES plans(id)

Development

Installation

npm install

Build

npm run build

Development Watch Mode

npm run watch

Debugging

Use the MCP Inspector:

npm run inspector

Best Practices

Creating Plans

  • Provide clear, descriptive names
  • Include detailed descriptions of objectives
  • Break down into multiple specific steps
  • Avoid creating plans with single steps

Creating Steps

  • Make steps specific and measurable
  • Define clear completion conditions
  • Keep steps focused on single objectives
  • Use testable completion conditions (e.g., "API endpoint returns 200 status code")

Managing Progress

  • Complete steps only when completion conditions are met
  • When a step fails, provide a clear alternative approach
  • Review step history to identify patterns in successes and failures

Contribution Guidelines

  1. Fork the repository
  2. Create a feature branch
  3. Submit a pull request
  4. Include tests for new features
  5. Update documentation
  6. Follow existing code style

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选