spec-driven-development-mcp-server

dmatta22201/spec-driven-development-mcp-server

3.2

If you are the rightful owner of spec-driven-development-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

The Model Context Protocol (MCP) server is designed for spec-driven development, integrating with Amazon Q CLI to leverage LLM-powered tools for generating software development documents.

Tools
4
Resources
0
Prompts
0

Spec-Driven Development MCP Server

A Model Context Protocol (MCP) server for spec-driven development that integrates with Amazon Q CLI. Provides LLM-powered tools to generate requirements, design, and task documents from conversations or product descriptions.

Components

1. MCP Server (mcp-server/)

Local Model Context Protocol server with four specialized tools for document generation and web content fetching.

Tools:

  • generate_requirements - Generate requirements.md from conversation/description
  • generate_design - Generate design.md from requirements document
  • generate_tasks - Generate tasks.md from requirements and design documents
  • query_web - Fetch and parse web page content

2. Q CLI Integration (q-cli-integration/)

Configuration and setup scripts for integrating the MCP server with AWS Q CLI.

Setup

  1. Install MCP Server Dependencies:

    cd mcp-server
    npm install
    
  2. Setup Q CLI Integration:

    cd q-cli-integration
    chmod +x setup.sh
    ./setup.sh
    

Usage

Generate Requirements Document

q chat "Generate requirements for a todo application that allows users to create, edit, delete, and organize tasks by categories with due dates"

Generate Design Document

q chat "Generate a design document from the requirements.md file located at ./requirements.md for project TodoApp"

Generate Tasks Document

q chat "Generate tasks from requirements.md and design.md files for project TodoApp"

Query Web Content

q chat "Use the query_web tool to fetch content from https://example.com"

LLM-Powered Features

All document generation tools use intelligent LLM analysis to:

  • Ask follow-up questions when critical information is missing
  • Make informed decisions based on project context
  • Generate specific content tailored to actual requirements
  • Follow best practices for software development documentation

Smart Follow-up Questions

The tools will ask clarifying questions such as:

  • "Should this be a web application, desktop application, or mobile app?"
  • "What level of security is required?"
  • "How many concurrent users should the system support?"
  • "What technologies or frameworks do you prefer?"

Generated Documents

Requirements Document

  • Project overview and executive summary
  • Functional requirements with acceptance criteria
  • Non-functional requirements (performance, security, scalability)
  • User stories in proper format
  • Constraints and dependencies
  • Success metrics

Design Document

  • System architecture and component design
  • Technology stack recommendations
  • API design with specific endpoints
  • Security and performance considerations
  • Deployment strategy
  • Risk assessment

Tasks Document

  • Complete TDD-based task breakdown
  • Technology-specific setup tasks
  • Feature implementation with RED-GREEN-REFACTOR cycles
  • Integration tasks for third-party services
  • Testing and deployment phases
  • Project timeline and estimates

File Structure

spec-driven-development/
ā”œā”€ā”€ mcp-server/
│   ā”œā”€ā”€ package.json
│   └── src/
│       ā”œā”€ā”€ index.js
│       └── tools/
│           ā”œā”€ā”€ queryWeb.js
│           ā”œā”€ā”€ generateRequirements.js
│           ā”œā”€ā”€ generateDesign.js
│           └── generateTasks.js
ā”œā”€ā”€ q-cli-integration/
│   ā”œā”€ā”€ mcp.json
│   └── setup.sh
ā”œā”€ā”€ references/
│   └── templates/
│       ā”œā”€ā”€ requirements.md
│       ā”œā”€ā”€ design.md
│       └── tasks.md
ā”œā”€ā”€ python-best-practices.md
ā”œā”€ā”€ nodejs-best-practices.md
└── README.md

Requirements

  • Node.js 22.x or higher
  • Amazon Q CLI installed and configured
  • Linux/macOS (Windows support not tested)