Spec Workflow MCP

English | 简体中文

Guide AI to systematically complete software development through a structured Requirements → Design → Tasks workflow, ensuring code implementation stays aligned with business needs.

Why Use It?

❌ Without Spec Workflow

• AI jumps randomly between tasks, lacking systematic approach
• Requirements disconnect from actual code implementation
• Scattered documentation, difficult to track project progress
• Missing design decision records

✅ With Spec Workflow

• AI completes tasks sequentially, maintaining focus and context
• Complete traceability from user stories to code implementation
• Standardized document templates with automatic progress management
• Each stage requires confirmation, ensuring correct direction
• Persistent progress: Continue from where you left off with check, even in new conversations

Recent Updates

v1.0.7

• 🎯 Improved reliability for most models to manage tasks with spec workflow

v1.0.6

• ✨ Batch task completion: Complete multiple tasks at once for faster progress on large projects

v1.0.5

• 🐛 Edge case fixes: Distinguish between "task not found" and "task already completed" to prevent workflow interruption

v1.0.4

• ✅ Task management: Added task completion tracking for systematic project progression

v1.0.3

• 🎉 Initial release: Core workflow framework for Requirements → Design → Tasks

Quick Start

1. Install (Claude Code Example)

claude mcp add spec-workflow-mcp -s user -- npx -y spec-workflow-mcp@latest

See full installation guide for other clients.

2. Start a New Project

"Help me use spec workflow to create a user authentication system"

3. Continue Existing Project

"Use spec workflow to check ./my-project"

The AI will automatically detect project status and continue from where it left off.

Workflow Example

1. You describe requirements

You: "I need to build a user authentication system"

2. AI creates structured documents

AI: "I'll help you create spec workflow for user authentication..."

📝 requirements.md - User stories and functional requirements
🎨 design.md - Technical architecture and design decisions
✅ tasks.md - Concrete implementation task list

3. Review and implement step by step

After each stage, the AI requests your confirmation before proceeding, ensuring the project stays on the right track.

Document Organization

Basic Structure

my-project/specs/
├── requirements.md              # Requirements: user stories, functional specs
├── design.md                    # Design: architecture, APIs, data models
├── tasks.md                     # Tasks: numbered implementation steps
└── .workflow-confirmations.json # Status: automatic progress tracking

Multi-module Projects

my-project/specs/
├── user-authentication/         # Auth module
├── payment-system/             # Payment module
└── notification-service/       # Notification module

You can specify any directory: "Use spec workflow to create auth docs in ./src/features/auth"

AI Usage Guide

🤖 Make AI Use This Tool Better

Strongly recommended to add the following prompt to your AI assistant configuration. Without it, AI may:

• ❌ Not know when to invoke Spec Workflow
• ❌ Forget to manage task progress, causing disorganized work
• ❌ Not utilize Spec Workflow for systematic documentation
• ❌ Unable to continuously track project status

With this configuration, AI will intelligently use Spec Workflow to manage the entire development process.

**Configu

... View full README on GitHub