An AI-assisted software development workflow tool based on specification-driven development, providing a real-time dashboard to monitor project progress and document management.
Spec Workflow MCP is a tool designed specifically for AI-assisted software development. It helps teams manage projects efficiently through a specification-driven workflow. It provides complete lifecycle management from requirement documentation to design implementation and task decomposition.
How to use Spec Workflow MCP?
Simply install and start the service via npm, then you can manage your project specifications and workflows by interacting through the Web dashboard or AI tools.
Applicable scenarios
It is particularly suitable for AI-assisted software projects that require a structured development process, team collaborative development, and scenarios that require specification document management.
Main Features
Structured Development Workflow
Provides a complete specification creation process from requirements → design → tasks
Real-time Web Dashboard
Visually monitors specifications, tasks, and project progress
Approval System
Manages the document approval process, supporting feedback and revision tracking
Template System
Presets templates for various document types to quickly start projects
Advantages
Complete workflow management from specification to implementation
Real-time visual project progress
Simplifies specification management for AI-assisted development
Cross-platform support (Windows/macOS/Linux)
Limitations
Requires running both the MCP server and dashboard service simultaneously
May be a bit complex for small projects
Requires basic command-line operation knowledge
How to Use
Installation
Install Spec Workflow MCP via npm
Start the Dashboard
The Web dashboard must be started to enable full functionality
Configure AI Tools
Configure the MCP server in the AI development tools you use
Usage Examples
Create a New Feature Specification
Create a complete specification workflow for the payment system
Task Implementation
Execute specific tasks in the specification
Frequently Asked Questions
Why must the dashboard be started?
The dashboard provides core functions such as an approval system, task tracking, and progress monitoring. Without it, these functions cannot be used.
How to view my specification list?
You can view it through the dashboard or use the 'List my specs' command in the AI tools.
Related Resources
Approval System Demo Video
Demonstrates the workflow of the approval system
Dashboard Demo Video
Demonstrates the functions and interface of the dashboard
npm Package Page
Official npm package information
Installation
Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.
🚀 Spec Workflow MCP
A Model Context Protocol (MCP) server that offers structured spec - driven development workflow tools for AI - assisted software development. It features a real - time web dashboard for monitoring and managing your project's progress.
📚 Documentation
📺 Showcase
🔄 Approval System in Action
See how the approval system works: create documents, request approval through the dashboard, provide feedback, and track revisions.
📊 Dashboard & Spec Management
Explore the real - time dashboard: view specs, track progress, navigate documents, and monitor your development workflow.
--port <number> - Optional custom port (1024 - 65535). If not specified, an ephemeral port will be used
IMPORTANT: The dashboard is mandatory for the workflow to function. Without it:
Document approvals won't work
Task progress tracking will be disabled
Spec status updates won't be available
The approval system will be non - functional
Note: The MCP server and dashboard are now separate services. You must run both: the MCP server for AI tool integration AND the dashboard for workflow management, approvals, and progress tracking.
💻 Usage Examples
Basic Usage
You can simply mention spec - workflow or whatever name you gave the MCP server in your conversation. The AI will handle the complete workflow automatically or you can use some of the example prompts below:
Creating Specs
"Create a spec for user authentication" - Creates complete spec workflow for that feature
"Create a spec called payment - system" - Builds full requirements → design → tasks
"Build a spec for @prd" - Takes your existing PRD and creates the complete spec workflow from it
"Create a spec for shopping - cart - include add to cart, quantity updates, and checkout integration" - Detailed feature spec
Getting Information
"List my specs" - Shows all specs and their current status
"Show me the user - auth progress" - Displays detailed progress information
Implementation
"Execute task 1.2 in spec user - auth" - Runs a specific task from your spec
Copy prompts from dashboard - Use the "Copy Prompt" button in the task list on your dashboard
The agent automatically handles approval workflows, task management, and guides you through each phase.
request - approval - Request user approval for documents
get - approval - status - Check approval status
delete - approval - Clean up completed approvals
📊 Web Dashboard
The dashboard is a separate service that must be started manually alongside the MCP server. Each project gets its own dedicated dashboard running on an ephemeral port. The dashboard provides:
Live Project Overview - Real - time updates of specs and progress
Document Viewer - Read requirements, design, and tasks documents
Task Progress Tracking - Visual progress bars and task status
Steering Documents - Quick access to project guidance
Dark Mode - Automatically enabled for better readability
Dashboard Features
Spec Cards - Overview of each spec with status indicators
Document Navigation - Switch between requirements, design, and tasks
Task Management - View task progress and copy implementation prompts
Real - Time Updates - WebSocket connection for live project status
Use get - spec - context for detailed implementation context
Use manage - tasks to track task completion
Monitor progress via the web dashboard
📂 File Structure
your - project/
.spec - workflow/
steering/
product.md # Product vision and goals
tech.md # Technical decisions
structure.md # Project structure guide
specs/
{spec - name}/
requirements.md # What needs to be built
design.md # How it will be built
tasks.md # Implementation breakdown
approval/
{spec - name}/
{document - id}.json # Approval status tracking
🛠️ Development
# Install dependencies
npm install
# Build the project
npm run build
# Run in development mode (with auto - reload)
npm run dev
# Start the production server
npm start
# Clean build artifacts
npm run clean
🐞 Troubleshooting
Common Issues
Dashboard not starting
Ensure you're using the --dashboard flag when starting the dashboard service
The dashboard must be started separately from the MCP server
Check console output for the dashboard URL and any error messages
If using --port, ensure the port number is valid (1024 - 65535) and not in use by another application
Approvals not working
Verify the dashboard is running alongside the MCP server
The dashboard is required for document approvals and task tracking
Check that both services are pointing to the same project directory
MCP server not connecting
Verify the file paths in your configuration are correct
Ensure the project has been built with npm run build
Check that Node.js is available in your system PATH
Port conflicts
If you get a "port already in use" error, try a different port with --port <different - number>
Use netstat -an | find ":3000" (Windows) or lsof -i :3000 (macOS/Linux) to check what's using a port
Omit the --port parameter to automatically use an available ephemeral port
Dashboard not updating
The dashboard uses WebSockets for real - time updates
Refresh the browser if connection is lost
Check console for any JavaScript errors
Getting Help
Check the Issues page for known problems
Create a new issue using the provided templates
Use the workflow guides within the tools for step - by - step instructions
📄 License
GPL - 3.0
⭐ Star History
spec-workflow-guide
Get the complete workflow instructions (must be called first)