Spec Workflow MCP
An intelligent MCP server that helps development teams maintain high-quality project documentation by providing an AI-powered workflow for creating comprehensive specifications through requirements, design, and implementation documents.
README
Spec Workflow MCP
An intelligent MCP server for managing software project specifications through a structured workflow of requirements, design, and implementation documents.
What is Spec Workflow MCP?
Spec Workflow MCP helps development teams maintain high-quality project documentation by providing an AI-powered workflow that guides you through creating comprehensive specifications.
❌ Without Spec Workflow MCP
- Inconsistent documentation across projects
- Missing critical requirements details
- Unstructured design decisions
- Unclear implementation tasks
- Manual tracking of document completion
- AI jumps between tasks randomly without structure
- No connection between requirements and actual code implementation
✅ With Spec Workflow MCP
- Standardized document templates for requirements, design, and tasks
- AI-guided document generation based on best practices
- Automatic progress tracking and workflow management
- Smart validation of document completeness
- Seamless integration with Claude and other MCP-compatible tools
- AI follows task order systematically, completing one before moving to the next
- Requirements → Design → Tasks workflow ensures code aligns with business needs
Installation
Requirements
- Node.js ≥ v18.0.0
- npm or yarn
- Claude Desktop or any MCP-compatible client
Quick Start with npx
npx spec-workflow-mcp@latest
Install in Different MCP Clients
Claude Code (Recommended)
Use the Claude CLI to add the MCP server:
claude mcp add spec-workflow-mcp -s user -- npx -y spec-workflow-mcp@latest
Claude Desktop
Add to your Claude Desktop configuration:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "spec-workflow-mcp@latest"]
}
}
}
Cursor
Add to your Cursor configuration (~/.cursor/config.json):
{
"mcpServers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "spec-workflow-mcp@latest"]
}
}
}
Windsurf (Codeium)
Add to your Windsurf configuration (~/.codeium/windsurf/mcp_config.json):
{
"mcpServers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "spec-workflow-mcp@latest"],
"env": {},
"autoApprove": [],
"disabled": false,
"timeout": 60,
"transportType": "stdio"
}
}
}
VS Code (with MCP extension)
Add to your VS Code settings (settings.json):
{
"mcp.servers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "spec-workflow-mcp@latest"]
}
}
}
Zed
Add to your Zed configuration (~/.config/zed/settings.json):
{
"assistant": {
"version": "2",
"mcp": {
"servers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "spec-workflow-mcp@latest"]
}
}
}
}
}
Install from Source
git clone https://github.com/kingkongshot/specs-mcp.git
cd specs-mcp
npm install
npm run build
Then add to Claude Desktop configuration:
{
"mcpServers": {
"spec-workflow": {
"command": "node",
"args": ["/absolute/path/to/specs-mcp/dist/index.js"]
}
}
}
Usage
Once installed, the MCP server provides the following commands through Claude:
Initialize a New Feature
Initialize spec workflow for "user authentication feature"
This creates a structured requirements document with sections for:
- Feature overview
- User stories
- Functional requirements
- Non-functional requirements
- Technical constraints
Check Progress and Generate Next Document
Check spec workflow progress
The server analyzes your current documentation and:
- Shows completion status for each section
- Identifies missing or incomplete areas
- Automatically generates the next document in the workflow
Complete Tasks
Complete task #3 in the implementation plan
Mark specific tasks as completed and track overall progress.
Skip Stages
Skip the design stage and go to implementation
Flexibility to adapt the workflow to your project needs.
Workflow Stages
- Requirements Gathering → 2. System Design → 3. Implementation Planning
Each stage has:
- Structured templates
- Validation rules
- AI-powered content generation
- Progress tracking
Features
- 📝 Smart Templates: Pre-defined document structures following best practices
- 🤖 AI-Powered Generation: Intelligent content suggestions based on your project context
- ✅ Progress Tracking: Visual progress indicators and completion tracking
- 🔄 Flexible Workflow: Skip stages or adapt the process to your needs
- 📊 Quality Validation: Automatic checks for document completeness
- 🔗 MCP Integration: Works seamlessly with Claude and other MCP clients
- 🎯 Sequential Task Execution: AI completes tasks in order, maintaining focus and context
- 🔄 Requirements-Driven Development: From business needs to code implementation in structured steps
Example Workflow
-
Start with a feature idea:
"I need to build a user authentication system" -
Initialize the workflow:
Initialize spec workflow for "user authentication" -
Review and enhance the generated requirements
-
Check progress and generate design document:
Check workflow progress -
Continue through design and implementation stages
-
Track task completion:
Complete task #1: Set up authentication database schema
Development
Build from Source
npm install
npm run build
Run in Development Mode
npm run dev
Run Tests
npm test
Debug with MCP Inspector
npm run inspector
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
MIT License - see LICENSE file for details
Links
Built with ❤️ using the Model Context Protocol
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。