Cursor Plan Executor

Cursor Plan Executor

A Model Context Protocol server for Cursor that manages and executes task plans with SQLite3-based CRUD operations, status tracking, and workflow tools.

Category
访问服务器

README

Cursor Plan Executor

A Model Context Protocol (MCP) server for Cursor that helps manage and execute task plans with SQLite3 database management tools.

Features

  • Plan Management: Complete CRUD operations for task plan steps
  • SQLite3 Database: Persistent storage for plan management
  • Status Tracking: Track completion status of plan steps
  • Execution Data: Store progress notes and results for each step
  • Workflow Tools: Streamlined tools for plan execution workflow

Database Schema

The server includes a SQLite3 database with the following table:

CREATE TABLE plan (
  step INTEGER PRIMARY KEY AUTOINCREMENT,
  instructions VARCHAR(10000) NOT NULL,
  status TINYINT DEFAULT 0 CHECK (status IN (0, 1)),
  execution_data TEXT
);

Installation

Global Installation (Recommended for Cursor integration)

npm install -g .

Local Development

npm install
npm run build

Usage

As a Global Command

After installing globally, you can run:

cursor-plan-executor

With npx

npx cursor-plan-executor

Direct Execution

node dist/index.js

Cursor Integration

Configuration

Add the following to your Cursor settings:

{
  "mcp": {
    "servers": {
      "cursor-plan-executor": {
        "command": "cursor-plan-executor",
        "args": [],
        "env": {}
      }
    }
  }
}

Or use the alternative format:

{
  "mcpServers": {
    "cursor-plan-executor": {
      "command": "cursor-plan-executor",
      "args": [],
      "env": {}
    }
  }
}

Available Tools

initialize_plan

Initialize a new task with your plan. Call this tool whenever you start a new task and already have the plan for it. Define all separate steps in the plan. Do not initialize a plan twice, as once initialized it will delete all previous plan data. Create the plan for the whole task.

Parameters:

  • plan_steps (required): Array of plan steps (instructions) for the task

Example Usage:

{
  "name": "initialize_plan",
  "arguments": {
    "plan_steps": [
      "Create a new React component",
      "Add state management",
      "Implement the UI",
      "Add tests",
      "Deploy the component"
    ]
  }
}

show_all_steps

Show all plan steps in a readable format with status indicators.

Parameters: None

Example Usage:

{
  "name": "show_all_steps",
  "arguments": {}
}

Response:

All Plan Steps:

1. ⏳ PENDING - Create a new React component

2. ✅ DONE - Add state management
   Execution Data: Redux store configured successfully

3. ⏳ PENDING - Implement the UI

get_next_step

Get the next pending step that you should follow.

Parameters: None

Example Usage:

{
  "name": "get_next_step",
  "arguments": {}
}

Response:

Next step to follow: 1 - Create a new React component

get_current_validation_criteria

Get the validation criteria for the currently unfinished task. This will list the validation criteria for the next pending step.

Parameters: None

Example Usage:

{
  "name": "get_current_validation_criteria",
  "arguments": {}
}

Response:

Current unfinished task:
Step 1 - Create a new React component
Validation Criteria: Component should have proper TypeScript types and error handling

Response (when no validation criteria):

Current unfinished task:
Step 1 - Create a new React component
No validation criteria specified for this step.

mark_current_step_done

Mark the current (next pending) step as done.

Parameters: None

Example Usage:

{
  "name": "mark_current_step_done",
  "arguments": {}
}

Response:

Step 1 marked as done: Create a new React component

mark_step_as_not_done

Mark a specific step as not done (pending). Call this tool when you need to revert a completed step back to pending status.

Parameters:

  • step (required): Step number to mark as not done

Example Usage:

{
  "name": "mark_step_as_not_done",
  "arguments": {
    "step": 2
  }
}

update_step_data

Update the instructions for a specific step by step ID.

Parameters:

  • step (required): Step number to update
  • instructions (required): New instructions for the step

Example Usage:

{
  "name": "update_step_data",
  "arguments": {
    "step": 1,
    "instructions": "Create a new React component with TypeScript"
  }
}

update_step_execution_data

Update the execution data for a plan step (useful for tracking progress and notes).

Parameters:

  • step (required): Step number to update
  • execution_data (required): Execution data to store (progress notes, results, etc.)

Example Usage:

{
  "name": "update_step_execution_data",
  "arguments": {
    "step": 1,
    "execution_data": "Component created successfully with proper TypeScript types"
  }
}

get_plan_step

Get a specific plan step by step number with full details.

Parameters:

  • step (required): Step number to retrieve

Example Usage:

{
  "name": "get_plan_step",
  "arguments": {
    "step": 1
  }
}

delete_plan_step

Delete a plan step by step number.

Parameters:

  • step (required): Step number to delete

Example Usage:

{
  "name": "delete_plan_step",
  "arguments": {
    "step": 1
  }
}

clear_all_plan_steps

Clear all plan steps from the database (use with caution).

Parameters: None

Example Usage:

{
  "name": "clear_all_plan_steps",
  "arguments": {}
}

Typical Workflow

  1. Initialize Plan: Use initialize_plan to set up your complete task plan
  2. Review Steps: Use show_all_steps to see the current status
  3. Get Next Step: Use get_next_step to see what to do next
  4. Complete Step: Use mark_current_step_done when finished with a step
  5. Add Notes: Use update_step_execution_data to add progress notes (optional)
  6. Repeat: Continue steps 3-5 until all steps are complete

Development

Prerequisites

  • Node.js 18 or higher
  • npm

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