规范驱动开发
STDIOAI引导的规范驱动开发MCP服务器
AI引导的规范驱动开发MCP服务器
An MCP server that brings AI-guided spec-driven development workflow to any AI-powered IDEs beyonnd Kiro. Transform your development process with structured, step-by-step guidance from idea to implementation.
Spec-driven development is a methodology that emphasizes creating detailed specifications before writing code. This approach helps ensure clear requirements, better design decisions, and more maintainable code. Our MCP server guides you through this process with AI assistance.
To install spec-coding-mcp for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @kevinlin/spec-coding-mcp --client claude
# Always get the latest version npx spec-coding-mcp@latest # Or simply (will also get latest) npx spec-coding-mcp
npm install -g spec-coding-mcp spec-coding-mcp
Add to your Cursor MCP settings:
{ "mcpServers": { "spec-coding-mcp": { "command": "npx", "args": ["spec-coding-mcp@latest"], "env": {}, "disabled": false } } }
The spec-driven development process follows five distinct stages. Here's how it works with a real example - building a user authentication feature:
Purpose: Establish clear, specific objectives for your feature.
Example Interaction:
User: I want to build a user authentication feature
Assistant: Let me start the spec-driven development workflow for you.
[calls spec_coding_workflow_start]
Let's define your feature goals:
1. What specific authentication methods do you want to support?
2. Do you need social login (Google, GitHub, etc.)?  
3. What user roles and permissions are required?
User: I need email/password login with JWT tokens, plus Google OAuth, and basic user/admin roles.
Assistant: Perfect! Let me confirm:
- Feature: User authentication system  
- Methods: Email/password + Google OAuth
- Tokens: JWT-based
- Roles: User and Admin
- Feature name: "user-authentication"
Is this correct?
User: Yes, that's exactly what I need.
[calls spec_coding_goal_confirmed with feature_name="user-authentication"]
Purpose: Transform your goals into specific, testable requirements using the EARS (Easy Approach to Requirements Syntax) format.
Example Interaction:
Assistant: Great! Now let's gather detailed requirements.
[calls spec_coding_requirements_start]
[Assistant generates detailed EARS-format requirements in docs/specs/user-authentication/requirements.md]
- WHEN a user provides valid email/password THEN the system SHALL authenticate them
- GIVEN a user wants Google OAuth WHEN they click "Sign in with Google" THEN the system SHALL redirect to Google
- WHERE user roles are needed IF user is admin THEN they SHALL access admin features
User: The requirements look comprehensive. Approved!
[calls spec_coding_requirements_confirmed]
Purpose: Create detailed technical specifications including architecture, component design, data models, and API specifications.
Example Interaction:
Assistant: Now let's create the technical design.
[calls spec_coding_design_start]
[Assistant creates detailed design document including:]
- Database schema for users, sessions, oauth_tokens
- Authentication middleware architecture  
- JWT token structure and validation flow
- Google OAuth integration endpoints
- Role-based access control implementation
User: Design looks good, proceed!
[calls spec_coding_design_confirmed]
Purpose: Decompose the feature into specific, prioritized development tasks with clear dependencies.
Example Interaction:
Assistant: Let's break this down into executable tasks.
[calls spec_coding_tasks_start]
[Assistant creates numbered task list:]
1. Set up database models (User, Session, OAuthToken)
2. Implement JWT token service
3. Create email/password authentication endpoints  
4. Integrate Google OAuth flow
5. Build role-based middleware
6. Add frontend login/register forms
7. Write integration tests
User: Task breakdown is perfect!
[calls spec_coding_tasks_confirmed]
Purpose: Execute the planned tasks systematically, implementing the feature according to specifications.
Example Interaction:
Assistant: Time to implement! Let's start coding.
[calls spec_coding_execute_start]
[Assistant implements each task step by step:]
- Creates User model with email, password_hash, role fields
- Builds JWT service with sign/verify methods
- Implements /auth/login and /auth/register endpoints
- Integrates Google OAuth with Passport.js
- Creates role-checking middleware
- Builds React login/register components
- Writes comprehensive test suite
Throughout the workflow, the following documentation structure is created:
docs/specs/{feature_name}/
├── requirements.md    # EARS-format requirements
├── design.md         # Technical architecture  
└── tasks.md          # Implementation checklist
Make sure you have Node.js 18+ installed.
# Install dependencies with pnpm (recommended) pnpm install # Or with npm npm install
# Development mode with pnpm pnpm dev # Or with npm npm run dev # Build with pnpm pnpm build # Or with npm npm run build # Start built version with pnpm pnpm start # Or with npm npm start # Test with pnpm (when available) pnpm test # Or with npm npm test
To publish the package to npm:
# Build the project pnpm build # Publish to npm (will automatically run prepublishOnly script) npm publish
Contributions are welcome! Please feel free to submit a Pull Request.
MIT
This project was inspired by and builds upon concepts from vibedevtools by @yinwm, a collection of development efficiency tools.