Spec Workflow MCP
Provides structured spec-driven development workflow tools for AI-assisted software development with sequential spec creation (Requirements → Design → Tasks). Features a real-time web dashboard for monitoring project progress and managing development workflows.
README
Spec Workflow MCP
A Model Context Protocol (MCP) server that provides structured spec-driven development workflow tools for AI-assisted software development, featuring a real-time web dashboard for monitoring and managing your project's progress.
📺 Showcase
🔄 Approval System in Action
<a href="https://www.youtube.com/watch?v=C-uEa3mfxd0" target="_blank"> <img src="https://img.youtube.com/vi/C-uEa3mfxd0/maxresdefault.jpg" alt="Approval System Demo" width="600"> </a>
See how the approval system works: create documents, request approval through the dashboard, provide feedback, and track revisions.
📊 Dashboard & Spec Management
<a href="https://www.youtube.com/watch?v=g9qfvjLUWf8" target="_blank"> <img src="https://img.youtube.com/vi/g9qfvjLUWf8/maxresdefault.jpg" alt="Dashboard Demo" width="600"> </a>
Explore the real-time dashboard: view specs, track progress, navigate documents, and monitor your development workflow.
☕ Support This Project
<a href="https://buymeacoffee.com/Pimzino" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
Features
- Structured Development Workflow - Sequential spec creation (Requirements → Design → Tasks)
- Real-Time Web Dashboard - Monitor specs, tasks, and progress with live updates
- Document Management - View and manage all spec documents from the dashboard
- Task Progress Tracking - Visual progress bars and detailed task status
- Steering Documents - Project vision, technical decisions, and structure guidance
- Bug Workflow - Complete bug reporting and resolution tracking
- Template System - Pre-built templates for all document types
- Cross-Platform - Works on Windows, macOS, and Linux
Quick Start
-
Add to your AI tool configuration (see MCP Client Setup below):
{ "mcpServers": { "spec-workflow": { "command": "npx", "args": ["-y", "@pimzino/spec-workflow-mcp@latest", "/path/to/your/project"] } } }Note: Can be used without path to your project, but some MCP clients may not start the server from the current directory.
-
Start using the workflow:
- Use
spec-workflow-guidetool first to understand the complete process - Use
steering-guidetool to create project steering documents (optional) - Monitor progress via the automatic web dashboard (opens automatically for each project)
- Use
Note: The dashboard automatically opens in your browser when you start the MCP server. If it does not open automatically or you are running on a headless system, you can retrieve the dashboard URL from the session.json file located in the .spec-workflow directory of your project.
How to Use
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.
MCP Client Setup
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "@pimzino/spec-workflow-mcp@latest", "/path/to/your/project"]
}
}
}
Cursor IDE
Add to your Cursor settings (settings.json):
{
"mcp.servers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "@pimzino/spec-workflow-mcp@latest", "/path/to/your/project"]
}
}
}
Claude Code CLI
Add to your MCP configuration:
claude mcp add spec-workflow npx "-y @pimzino/spec-workflow-mcp@latest /path/to/your/project"
Augment Code
Configure in your Augment settings:
{
"mcpServers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "@pimzino/spec-workflow-mcp@latest", "/path/to/your/project"]
}
}
}
Continue IDE Extension
Add to your Continue configuration:
{
"mcpServers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "@pimzino/spec-workflow-mcp@latest", "/path/to/your/project"]
}
}
}
Cline/Claude Dev
Add to your MCP server configuration:
{
"mcpServers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "@pimzino/spec-workflow-mcp@latest", "/path/to/your/project"]
}
}
}
Note: Replace
/path/to/your/projectwith the actual path to your project directory where you want the spec workflow to operate.
Available Tools
Workflow Guides
spec-workflow-guide- Complete guide for the spec-driven workflow processsteering-guide- Guide for creating project steering documents
Spec Management
create-spec-doc- Create/update spec documents (requirements, design, tasks)spec-list- List all specs with status informationspec-status- Get detailed status of a specific specmanage-tasks- Comprehensive task management for spec implementation
Context & Templates
get-template-context- Get markdown templates for all document typesget-steering-context- Get project steering context and guidanceget-spec-context- Get context for a specific spec
Steering Documents
create-steering-doc- Create project steering documents (product, tech, structure)
Approval System
request-approval- Request user approval for documentsget-approval-status- Check approval statusdelete-approval- Clean up completed approvals
Web Dashboard
The server includes a real-time web dashboard that automatically opens in your browser when you start 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
Workflow Process
1. Project Setup (Recommended)
steering-guide → create-steering-doc (product, tech, structure)
Creates foundational documents to guide your project development.
2. Feature Development
spec-workflow-guide → create-spec-doc → [review] → implementation
Sequential process: Requirements → Design → Tasks → Implementation
3. Implementation Support
- Use
get-spec-contextfor detailed implementation context - Use
manage-tasksto 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 opening automatically
- The dashboard uses ephemeral ports and opens automatically when the MCP server starts
- Check console output for the dashboard URL if it doesn't open in your browser
-
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
-
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
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.