Software Planning Tool
Facilitates software development planning through an interactive and structured approach.
Software Planning Tool 🚀
A Model Context Protocol (MCP) server designed to facilitate software development planning through an interactive, structured approach. This tool helps break down complex software projects into manageable tasks, track implementation progress, and maintain detailed development plans.
Features ✨
- Interactive Planning Sessions: Start and manage development planning sessions
- Todo Management: Create, update, and track development tasks
- Complexity Scoring: Assign complexity scores to tasks for better estimation
- Code Examples: Include relevant code snippets in task descriptions
- Implementation Plans: Save and manage detailed implementation plans
Installation 🛠️
Installing via Smithery
To install Software Planning Tool for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @NightTrek/Software-planning-mcp --client claude
Manual Installation
- Clone the repository
- Install dependencies:
pnpm install
- Build the project:
pnpm run build
- Add to your MCP settings configuration (typically located at
~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json):
{
"mcpServers": {
"software-planning-tool": {
"command": "node",
"args": [
"/path/to/software-planning-tool/build/index.js"
],
"disabled": false,
"autoApprove": []
}
}
}
Available Tools 🔧
start_planning
Start a new planning session with a specific goal.
{
goal: string // The software development goal to plan
}
add_todo
Add a new todo item to the current plan.
{
title: string, // Title of the todo item
description: string, // Detailed description
complexity: number, // Complexity score (0-10)
codeExample?: string // Optional code example
}
get_todos
Retrieve all todos in the current plan.
// No parameters required
update_todo_status
Update the completion status of a todo item.
{
todoId: string, // ID of the todo item
isComplete: boolean // New completion status
}
save_plan
Save the current implementation plan.
{
plan: string // The implementation plan text
}
remove_todo
Remove a todo item from the current plan.
{
todoId: string // ID of the todo item to remove
}
Example Usage 📝
Here's a complete example of using the software planning tool:
- Start a planning session:
await client.callTool("software-planning-tool", "start_planning", {
goal: "Create a React-based dashboard application"
});
- Add a todo item:
const todo = await client.callTool("software-planning-tool", "add_todo", {
title: "Set up project structure",
description: "Initialize React project with necessary dependencies",
complexity: 3,
codeExample: `
npx create-react-app dashboard
cd dashboard
npm install @material-ui/core @material-ui/icons
`
});
- Update todo status:
await client.callTool("software-planning-tool", "update_todo_status", {
todoId: todo.id,
isComplete: true
});
- Save the implementation plan:
await client.callTool("software-planning-tool", "save_plan", {
plan: `
# Dashboard Implementation Plan
## Phase 1: Setup (Complexity: 3)
- Initialize React project
- Install dependencies
- Set up routing
## Phase 2: Core Features (Complexity: 5)
- Implement authentication
- Create dashboard layout
- Add data visualization components
`
});
Development 🔨
Project Structure
software-planning-tool/
├── src/
│ ├── index.ts # Main server implementation
│ ├── prompts.ts # Planning prompts and templates
│ ├── storage.ts # Data persistence
│ └── types.ts # TypeScript type definitions
├── build/ # Compiled JavaScript
├── package.json
└── tsconfig.json
Building
pnpm run build
Testing
Test all features using the MCP inspector:
pnpm run inspector
License 📄
MIT
Made with ❤️ using the Model Context Protocol
Похожие серверы
Alpha Vantage MCP Server
спонсорAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Tripwire
Context injection for AI agents via MCP. Define path-based policies in YAML — when an agent reads a matching file, relevant knowledge is auto-injected. Prevents mistakes before they happen. Works with Claude Code, Cursor, and any MCP client.
Diffchunk
Navigate large diff files with intelligent chunking and navigation tools.
My First MCP
A Model Context Protocol server implemented in Node.js with Docker support.
Supervisord MCP
A tool for managing Supervisord processes, integrated with AI agents via the Model Context Protocol (MCP). It offers standardized process control, real-time monitoring, and robust operations.
Ollama MCP Server
Integrate local Ollama LLM instances with MCP-compatible applications.
SCAST
Analyzes source code to generate UML and flow diagrams with AI-powered explanations.
MCP Swagger Server
Converts OpenAPI/Swagger specifications to Model Context Protocol (MCP) format, providing a modern Web UI and a backend service.
nf-core MCP Server
Manage and navigate local nf-core pipeline repositories.
ButterKit
Ship App Store screenshots from your AI coding agent: generate, localize to all 50 App Store languages, and upload to App Store Connect
WinTerm MCP
Provides programmatic access to the Windows terminal, enabling AI models to interact with the command line interface.