
Spec-driven Development MCP Server
An MCP server that enables AI-powered IDEs to implement a structured development workflow from requirements gathering to code implementation, guiding users through goal collection, requirements specification, design documentation, task planning, and execution.
README
Spec-driven Development MCP Server
An MCP server that brings AI spec-driven development workflow to any AI-powered IDE besides Kiro
Features
- Complete Development Workflow: From goal collection to task execution
- AI-Powered Guidance: Step-by-step instructions for each development phase
- Template-Based: Uses proven templates for requirements, design, and tasks
- IDE Integration: Seamlessly integrates with Cursor, Copilot or any AI-powered IDE
Installation
Using npx (Recommended)
# Always get the latest version
npx spec-driven-dev-mcp@latest
# Or simply (will also get latest)
npx spec-driven-dev-mcp
Using npm
npm install -g spec-driven-dev-mcp
spec-driven-dev-mcp
Usage
With Cursor
Add to your Cursor MCP settings:
{
"mcpServers": {
"spec-driven-dev-mcp": {
"command": "npx",
"args": ["spec-driven-dev-mcp@latest"],
"env": {},
"disabled": false
}
}
}
Available Tools
- spec_driven_dev_workflow_start - Start the development workflow
- spec_driven_dev_goal_confirmed - Confirm feature goals
- spec_driven_dev_requirements_start - Begin requirements gathering
- spec_driven_dev_requirements_confirmed - Confirm requirements completion
- spec_driven_dev_design_start - Start design documentation
- spec_driven_dev_design_confirmed - Confirm design completion
- spec_driven_dev_tasks_start - Begin task planning
- spec_driven_dev_tasks_confirmed - Confirm task planning completion
- spec_driven_dev_execute_start - Start task execution
Workflow Stages
- Goal Collection - Define what you want to build
- Requirements Gathering - Create detailed EARS-format requirements
- Design Documentation - Technical architecture and design
- Task Planning - Break down into executable tasks
- Task Execution - Implement the code
Project Structure
Generated projects follow this structure:
.docs/specs/{feature_name}/
├── requirements.md
├── design.md
└── tasks.md
Example Usage
Here's a complete example of using the VibeSpecs workflow:
1. Start the Workflow
User: I want to build a user authentication feature
Assistant: Let me start the VibeSpecs workflow for you.
[calls spec_driven_dev_workflow_start]
2. Goal Collection
Assistant: Welcome to VibeSpecs! 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_driven_dev_goal_confirmed with feature_name="user-authentication"]
3. Requirements Gathering
Assistant: Great! Now let's gather detailed requirements.
[calls spec_driven_dev_requirements_start]
[Assistant generates detailed EARS-format requirements in .docs/specs/user-authentication/requirements.md]
User: The requirements look comprehensive. Approved!
[calls spec_driven_dev_requirements_confirmed]
4. Design Documentation
Assistant: Now let's create the technical design.
[calls spec_driven_dev_design_start]
[Assistant creates detailed design document with architecture, components, data models, etc.]
User: Design looks good, proceed!
[calls spec_driven_dev_design_confirmed]
5. Task Planning
Assistant: Let's break this down into executable tasks.
[calls spec_driven_dev_tasks_start]
[Assistant creates numbered task list with priorities and dependencies]
User: Task breakdown is perfect!
[calls spec_driven_dev_tasks_confirmed]
6. Task Execution
Assistant: Time to implement! Let's start coding.
[calls spec_driven_dev_execute_start]
[Assistant begins implementing tasks one by one, following the plan]
Generated Project Structure
.docs/specs/user-authentication/
├── requirements.md # EARS-format requirements
├── design.md # Technical architecture
└── tasks.md # Implementation checklist
Development
Prerequisites
Make sure you have Node.js 18+ installed.
Setup
# Install dependencies with pnpm (recommended)
pnpm install
# Or with npm
npm install
Running 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 test
License
MIT
Attribution
This project was inspired by and builds upon concepts from vibedevtools by @yinwm, a collection of development efficiency tools.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.