Specs Workflow MCP server

Guides users through structured software project documentation phases with automated document generation, progress tracking, and workflow state management using OpenAPI specifications as templates.
Back to servers
Setup instructions
Provider
kingkongshot
Release date
Aug 03, 2025
Language
PHP
Stats
119 stars

Spec Workflow MCP is a tool that helps guide AI to systematically complete software development through a structured Requirements → Design → Tasks workflow. It ensures code implementation stays aligned with business needs by maintaining focus and context throughout the development process.

Installation

Requirements

  • Node.js ≥ v18.0.0
  • npm or yarn
  • Claude Desktop or any MCP-compatible client

Installation Methods

Claude Code (Recommended)

claude mcp add spec-workflow-mcp -s user -- npx -y spec-workflow-mcp@latest

Claude Desktop

Add to your Claude Desktop configuration file (location varies by OS):

{
  "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"]
    }
  }
}

Other MCP Clients

Similar configuration can be added to Cline, Windsurf (Codeium), VS Code with MCP extension, and Zed. Each requires adding the appropriate configuration to their respective settings files.

Getting Started

Starting a New Project

Simply ask the AI:

"Help me use spec workflow to create a user authentication system"

Continuing an Existing Project

To resume work on a project:

"Use spec workflow to check ./my-project"

The AI will automatically detect your project's status and continue from where you left off.

How It Works

Workflow Process

  1. Requirements Phase: You describe what you need, and AI creates structured requirements documents
  2. Design Phase: AI creates technical architecture and design decisions based on requirements
  3. Tasks Phase: AI breaks down implementation into concrete, manageable tasks
  4. Implementation: Complete tasks systematically with AI assistance

Document Organization

Basic structure:

my-project/specs/
├── requirements.md              # Requirements: user stories, functional specs
├── design.md                    # Design: architecture, APIs, data models
├── tasks.md                     # Tasks: numbered implementation steps
└── .workflow-confirmations.json # Status: automatic progress tracking

For larger projects, you can organize by modules:

my-project/specs/
├── user-authentication/         # Auth module
├── payment-system/             # Payment module
└── notification-service/       # Notification module

Optimizing AI Usage

For better results, add the following prompt to your AI assistant configuration:

# Spec Workflow Usage Guidelines

## 1. Check Project Progress
When user mentions continuing previous project or is unsure about current progress, proactively use:
specs-workflow tool with action.type="check" and path="./specs"

## 2. Documentation Language
All spec workflow documents should be written in English consistently, including all content in requirements, design, and task documents.

## 3. Documentation Directory
All spec workflow documents should be placed in ./specs directory to maintain consistent project documentation organization.

## 4. Task Management
Always use the following to manage task progress:
specs-workflow tool with action.type="complete_task" and taskNumber="current task number"
Follow the workflow guidance to continue working until all tasks are completed.

## 5. Best Practices
- Proactive progress check: When user says "continue from last time", first use check to see current status
- Language consistency: Use the same language throughout all project documents
- Flexible structure: Choose single-module or multi-module organization based on project scale
- Task granularity: Each task should be completable within 1-2 hours

Recent Updates

  • v1.0.7: Improved reliability for most models to manage tasks with spec workflow
  • v1.0.6: Batch task completion for faster progress on large projects
  • v1.0.5: Edge case fixes to prevent workflow interruption
  • v1.0.4: Added task completion tracking for systematic project progression
  • v1.0.3: Initial release with core workflow framework

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "spec-workflow" '{"command":"npx","args":["-y","spec-workflow-mcp@latest"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "spec-workflow": {
            "command": "npx",
            "args": [
                "-y",
                "spec-workflow-mcp@latest"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "spec-workflow": {
            "command": "npx",
            "args": [
                "-y",
                "spec-workflow-mcp@latest"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later