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-workflow-mcpConfiguration
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 brings structured, spec-driven development to AI-assisted coding by enforcing a sequential workflow of Requirements → Design → Tasks before any implementation begins. It integrates with AI coding agents to guide them through spec creation, task execution, and approval processes, while a real-time web dashboard (port 5000) and optional VSCode extension give developers live visibility into spec status, task progress, implementation logs, and code statistics. Developers who find AI coding sessions drift or produce inconsistent architecture will benefit from the structured guardrails this server enforces.
Prerequisites
- Node.js 18 or later with npx available
- An MCP-compatible AI coding client: Claude Desktop, Claude Code, Cursor, Cline, Augment Code, or Continue
- A project directory path to pass to the server (it stores specs relative to this path)
- Optional: VS Code with the Spec Workflow MCP extension for the sidebar dashboard
Add the server to your MCP client configuration
Configure your AI client to launch the spec-workflow-mcp server via npx. Pass your project directory path as the last argument so the server knows where to store specs.
{
"mcpServers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "@pimzino/spec-workflow-mcp@latest", "/path/to/your/project"]
}
}
}Start the web dashboard (for CLI users)
Run the dashboard separately to get a browser-based UI for monitoring specs and approvals. It runs on port 5000 and handles all projects connected to the same MCP server instance.
npx -y @pimzino/spec-workflow-mcp@latest --dashboard
# Dashboard available at:
open http://localhost:5000Install the VSCode extension (optional)
For VSCode users, install the Spec Workflow MCP extension from the marketplace for an integrated sidebar dashboard that eliminates the need for the separate web dashboard.
# Install from VSCode marketplace:
https://marketplace.visualstudio.com/items?itemName=Pimzino.spec-workflow-mcp
# Or from VSCode command palette:
# Extensions: Install Extension → search 'Spec Workflow MCP'Create your first spec
In your AI assistant, ask it to create a spec. The server will guide the agent through the Requirements, Design, and Task creation stages sequentially before allowing implementation.
Execute tasks and track progress
After spec approval, ask your AI to execute individual tasks. The dashboard shows visual progress bars, implementation logs, and code statistics in real time.
Spec Workflow Examples
Client configuration (Claude Code CLI)
Register the spec-workflow-mcp server in Claude Code using the CLI. The -- separator ensures the project path goes to the server, not npx.
{
"mcpServers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "@pimzino/spec-workflow-mcp@latest", "/Users/yourname/projects/my-app"]
}
}
}Prompts to try
Typical prompts to use with your AI assistant once spec-workflow-mcp is connected:
- "Create a spec for user authentication with email/password and JWT tokens"
- "List my specs and show their current status"
- "Execute task 1.2 in the user-auth spec"
- "Show me the implementation logs for the database spec"
- "Request approval for the design phase of the payment spec"Troubleshooting Spec Workflow
Server starts but specs are not persisted between sessions
Ensure you are passing the correct absolute path to your project directory as the last argument to npx. Specs are stored in a .spec-workflow directory inside that path — verify the directory was created after the first spec.
Dashboard shows no projects or specs
The dashboard connects to the same running MCP server. Ensure the MCP server is actively connected to your AI client (not just the dashboard standalone process). Only one dashboard instance is needed — if you started multiple, stop duplicates and keep one.
Windows: npx command fails or path is not passed correctly
On Windows, use the cmd.exe wrapper: set args to ["/c", "npx", "@pimzino/spec-workflow-mcp@latest", "C:\\path\\to\\project"] with command set to cmd.exe. The -y flag can be omitted on Windows if it causes issues.
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.