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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。