The Spec-driven Development MCP Server provides an AI-guided, structured workflow for complete software development from concept to execution.
Core Workflow Capabilities:
Start & Define: Initiate development workflows (
spec_driven_dev_workflow_start) and confirm feature goals with specific names and summariesRequirements Gathering: Collect and confirm detailed requirements in EARS format using
spec_driven_dev_requirements_startandspec_driven_dev_requirements_confirmedTechnical Design: Create and confirm comprehensive design documentation covering architecture, components, and data models
Task Planning: Break down features into executable, manageable tasks with confirmation workflows
Execution: Systematically guide task implementation with
spec_driven_dev_execute_start, optionally targeting specific tasks
Documentation & Organization:
Generates structured outputs (
requirements.md,design.md,tasks.md) in feature-specific directoriesCreates organized project documentation throughout the development lifecycle
Integration:
Compatible with AI-powered IDEs like Cursor and Claude Desktop
Supports JSON configuration for seamless setup and interactive development experience
Mentioned in the context of OAuth login options for the user authentication feature example
Provides OAuth authentication integration as demonstrated in the example authentication workflow
Serves as the runtime environment for the MCP server, with version 18+ required for development
Provides package installation and management for the MCP server
Recommended as the preferred package manager for development of the MCP server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Spec-driven Development MCP Serverhelp me build a user authentication feature"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Spec-driven Development Workflow
An AI-guided spec-driven development workflow available as both a Claude Code Skill and MCP Server. Transform your development process with structured, step-by-step guidance from idea to implementation.
What is Spec-driven Development?
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. This workflow guides you through the process with AI assistance.
Related MCP server: Interactive Feedback MCP
π― Two Ways to Use This Workflow
Option 1: Claude Code Skill (Recommended for Claude Code Users)
Simple, integrated, no setup required!
The workflow is available as a native Claude Code Skill. Just invoke it in any conversation:
/spec-codingOr naturally:
I want to use the spec-coding workflow to build [feature]Benefits:
β No installation or configuration needed
β Native integration with Claude Code
β Seamless conversation flow
β Automatic progress tracking with TodoWrite
Learn more: Skill Documentation | Migration Guide
Option 2: MCP Server (For Other IDEs)
Use as an MCP server for Claude Desktop, Cursor, or other MCP-compatible tools.
Installation via Smithery:
npx -y @smithery/cli install @kevinlin/spec-coding-mcp --client claudeLearn more: See MCP Server Setup below.
Features
Complete Development Workflow: From goal collection to task execution
AI-Powered Guidance: Step-by-step instructions for each development phase
Structured Documentation: Generates organized specs in EARS format
Template-Based: Uses proven templates for requirements, design, and tasks
MCP Server Setup
This section is for users who want to use the workflow as an MCP server (Option 2 above).
Installation
Installing via Smithery
To install spec-coding-mcp for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @kevinlin/spec-coding-mcp --client claudeUsing npx (Recommended)
# Always get the latest version
npx spec-coding-mcp@latest
# Or simply (will also get latest)
npx spec-coding-mcpUsing npm
npm install -g spec-coding-mcp
spec-coding-mcpUsage
With Cursor
Add to your Cursor MCP settings:
{
"mcpServers": {
"spec-coding-mcp": {
"command": "npx",
"args": ["spec-coding-mcp@latest"],
"env": {},
"disabled": false
}
}
}Available Tools
spec_coding_workflow_start - Start the development workflow
spec_coding_goal_confirmed - Confirm feature goals
spec_coding_requirements_start - Begin requirements gathering
spec_coding_requirements_confirmed - Confirm requirements completion
spec_coding_design_start - Start design documentation
spec_coding_design_confirmed - Confirm design completion
spec_coding_tasks_start - Begin task planning
spec_coding_tasks_confirmed - Confirm task planning completion
spec_coding_execute_start - Start task execution
Workflow Stages & Example
The spec-driven development process follows five distinct stages. Here's how it works with a real example - building a user authentication feature:
1. Goal Collection - Define What You Want to Build
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"]2. Requirements Gathering - Create Detailed EARS-format Requirements
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]3. Design Documentation - Technical Architecture and Design
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]4. Task Planning - Break Down into Executable Tasks
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]5. Task Execution - Implement the Code
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 suiteGenerated Project Structure
Throughout the workflow, the following documentation structure is created:
docs/specs/{feature_name}/
βββ requirements.md # EARS-format requirements
βββ design.md # Technical architecture
βββ tasks.md # Implementation checklistDevelopment
Prerequisites
Make sure you have Node.js 18+ installed.
Setup
# Install dependencies with pnpm (recommended)
pnpm install
# Or with npm
npm installRunning the Project
# 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 testPublishing
To publish the package to npm:
# Build the project
pnpm build
# Publish to npm (will automatically run prepublishOnly script)
npm publishContributing & License
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
MIT
Attribution
This project was inspired by and builds upon concepts from vibedevtools by @yinwm, a collection of development efficiency tools.