Spec Workflow
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 and VSCode extension for monitoring and managing your project's progress d
What is Spec Workflow?
Spec Workflow is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server that provides structured spec-driven development workflow tools for ai-assisted software development, featuring a real-time web dashboard and vscode extension for m...
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 and VSCode extension for monitoring and managing your project's progress d
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol (MCP) server that provides structur
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx spec-workflowConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Spec Workflow
Spec Workflow MCP is a Model Context Protocol server that enforces a structured, specification-first development process for AI-assisted coding by guiding AI agents through a mandatory Requirements → Design → Tasks sequence before any code is written. It connects to AI coding agents via MCP and provides real-time project monitoring through a web dashboard on port 5000 and an optional VSCode sidebar extension, giving teams visibility into spec approval status, task progress, implementation logs, and per-task code statistics. Engineering teams and solo developers who want predictable, auditable outcomes from AI coding sessions will benefit from the structured guardrails and approval workflows this server provides.
Prerequisites
- Node.js 18 or later with npx available
- An MCP-compatible AI coding client: Claude Desktop, Claude Code, Cursor, Cline, Augment Code, Continue, or OpenCode
- An absolute path to the project directory where specs will be stored
- Optional: VS Code with the Spec Workflow MCP extension installed from the marketplace
Add the MCP server to your client config
Edit your MCP client's configuration file to launch spec-workflow-mcp via npx. Provide the absolute path to your project directory as the final argument.
{
"mcpServers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "@pimzino/spec-workflow-mcp@latest", "/absolute/path/to/project"]
}
}
}Launch the web dashboard
Start the real-time web dashboard in a separate terminal. It listens on port 5000 and displays all active specs, tasks, and implementation logs. You only need one dashboard instance per machine.
npx -y @pimzino/spec-workflow-mcp@latest --dashboard
# Then open:
open http://localhost:5000Install the VSCode extension (optional)
VSCode users can install the Spec Workflow MCP extension for an integrated sidebar that replaces the need for the standalone web dashboard.
# Search in VSCode Extensions panel:
Spec Workflow MCP
# Direct marketplace link:
https://marketplace.visualstudio.com/items?itemName=Pimzino.spec-workflow-mcpCreate a spec via your AI assistant
Tell your AI assistant to create a spec for a feature. The MCP server will enforce the sequential workflow: requirements first, then design, then tasks — blocking code generation until each stage is approved.
Approve stages and execute tasks
Review each stage (Requirements, Design) in the dashboard or VSCode panel and approve or request revisions. Once tasks are defined and approved, ask the AI to execute them one by one.
Monitor progress and review logs
The dashboard shows visual progress bars per spec, searchable implementation logs, and code statistics (lines added/modified) for each completed task.
Spec Workflow Examples
Client configuration (Cursor)
Add spec-workflow-mcp to Cursor's MCP settings for use inside the Cursor IDE:
{
"mcpServers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "@pimzino/spec-workflow-mcp@latest", "/Users/yourname/my-project"]
}
}
}Prompts to try
Example prompts to use with your AI assistant after connecting spec-workflow-mcp:
- "Create a spec for a REST API with user authentication and role-based access control"
- "List my specs"
- "Show the status of the user-auth spec"
- "Execute task 2.1 in spec payment-integration"
- "Show implementation logs for the last completed task"Troubleshooting Spec Workflow
AI skips the spec workflow and writes code directly
Ensure the MCP server is active and connected — check your client's MCP status panel. If the AI isn't invoking the spec-workflow tools, explicitly tell it: 'Use the spec-workflow MCP to create a spec before writing any code.'
Port 5000 is already in use when starting the dashboard
Another process (often AirPlay Receiver on macOS) may be using port 5000. Stop that process or change the dashboard port. On macOS: System Settings > AirDrop & Handoff > AirPlay Receiver > turn off.
Specs are created but disappear after restarting
Specs are stored in a .spec-workflow folder inside the project directory you passed as an argument. Make sure you always pass the same absolute path. If the path changes or is relative, a new empty spec store is created.
Frequently Asked Questions about Spec Workflow
What is Spec Workflow?
Spec Workflow is a Model Context Protocol (MCP) server that model context protocol (mcp) server that provides structured spec-driven development workflow tools for ai-assisted software development, featuring a real-time web dashboard and vscode extension for monitoring and managing your project's progress d It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Spec Workflow?
Follow the installation instructions on the Spec Workflow GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Spec Workflow?
Spec Workflow works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Spec Workflow free to use?
Yes, Spec Workflow is open source and available under the GPL-3.0 license. You can use it freely in both personal and commercial projects.
Spec Workflow Alternatives — Similar Developer Tools Servers
Looking for alternatives to Spec Workflow? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Spec Workflow in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Spec Workflow?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.