Provides scaffolding templates and boilerplate generation for Next.js 15 projects, enabling AI agents to create standardized project structures and add features following Next.js conventions
Offers scaffolding capabilities for React projects through Vite integration, allowing AI agents to generate React components, pages, and services with consistent patterns
Enables scaffolding and template generation for Vite-based projects, providing AI agents with tools to create and manage modern frontend build configurations and project structures
AI Code Toolkit
Scale your AI coding agents with scaffolding, architecture patterns, and validation rules
A collection of Model Context Protocol (MCP) servers and tools that help AI coding agents maintain consistency, follow conventions, and scale with your codebase.
Contents
Why This Exists
As projects evolve from MVP to production, they develop patterns, conventions, and opinionated approaches. Custom instructions alone struggle to ensure AI agents follow these requirements—especially as complexity grows and context windows fill up.
AI Code Toolkit provides building blocks to scale coding agent capabilities:
✅ Generate code that follows your team's conventions
✅ Enforce architectural patterns automatically
✅ Validate agent outputs programmatically
✅ Work with any AI coding agent (Claude, Cursor, etc.)
✅ Support any tech stack (Next.js, React, or custom frameworks)
Whether you're bootstrapping a new project or managing a complex monorepo, these tools ensure AI agents integrate seamlessly with your development workflow.
Core Pillars
1. 🏗️ Scaffolding Templates
Combine templating with LLMs to generate standardized code that follows your internal conventions while reducing maintenance overhead.
2. 🎨 Architecture + Design Patterns
Convention over configuration scales. Like Ruby on Rails or Angular, opinionated approaches make code predictable—for both humans and AI agents.
3. ✅ Rules
Pre-flight guidance + post-flight validation = consistent output. Rules provide programmatic checks (quantitative or qualitative) to enforce your processes.
Getting Started
Prerequisites
Node.js:
>= 18
(LTS recommended)Package Manager:
pnpm
(ornpm
/yarn
)Git:
>= 2.13.2
Quick Start
Option 1: Use as MCP Server (with Claude Desktop)
Install the package:
pnpm install @agiflowai/scaffold-mcpConfigure Claude Desktop: Add to your MCP settings:
{ "mcpServers": { "scaffold": { "command": "scaffold-mcp", "args": ["mcp-serve"] } } }Start using it: The MCP server tools will be available in Claude Desktop.
Option 2: Use as CLI
For detailed usage, see the scaffold-mcp documentation.
Packages
@agiflowai/scaffold-mcp
MCP server for scaffolding applications with boilerplate templates and feature generators.
Key Features:
🚀 Create projects from boilerplate templates
🎯 Add features to existing projects (pages, components, services)
📦 Template management (initialize, add from repositories)
🔧 Built-in templates: Next.js 15, Vite + React
🌐 Multiple transport modes: stdio, HTTP, SSE
💻 Standalone CLI mode
@agiflowai/scaffold-generator
Core utilities and types for scaffold generators. Internal library used by scaffold-mcp
.
Our Approach
🤖 Agent Agnostic
Works with any AI coding agent (Claude Code, Cursor, Windsurf, etc.). Each library provides:
MCP tools for integration with MCP-compatible agents
CLI commands for scripting deterministic workflows
🛠️ Tech Stack Agnostic
Built-in templates for popular frameworks:
Next.js 15
Vite + React
More coming soon
Don't see your stack? Use the built-in MCP tools to generate custom templates—the system is fully extensible.
🎯 Coding Tool Specific
Maximize effectiveness by combining three layers:
MCP Servers → Let tools guide the agent with their default prompts
Custom Instructions → Use
CLAUDE.md
,AGENTS.md
to specify when to use MCP toolsHooks → Intercept tool calls to enforce workflows (e.g., require scaffolding for new files)
Experiment with these layers to find the right balance for your project. There's no one-size-fits-all solution.
Development
This is an Nx monorepo using pnpm for package management.
Common Commands
Code Quality
We use Biome for lightning-fast linting and formatting:
⚡ 10-100x faster than ESLint (written in Rust)
🎯 All-in-one: Replaces ESLint + Prettier
🔧 Zero config: Sensible defaults out of the box
Configuration: biome.json
Publishing
See PUBLISHING.md for the complete release workflow:
Documentation
Scaffold MCP Guide - Complete guide to the scaffolding MCP server
Contributing Guide - How to contribute to this project
Publishing Guide - Release and versioning workflow
Version Support
Component | Requirement |
Node.js |
(LTS recommended) |
Git |
|
pnpm |
(or use npm/yarn) |
Security patches are applied to non-EOL versions. Features are added to the latest version only.
Contributing
We welcome contributions! Whether it's bug reports, feature requests, or pull requests—all contributions are appreciated.
How to contribute:
🍴 Fork the repository
🌿 Create a feature branch (
git checkout -b feature/amazing-feature
)💻 Make your changes
✅ Run tests and linting (
pnpm test && pnpm lint
)📝 Commit your changes (follow conventional commits)
🚀 Push to your branch (
git push origin feature/amazing-feature
)🎉 Open a Pull Request
See CONTRIBUTING.md for detailed guidelines.
License
AGPL-3.0 © AgiflowIO
Built with ❤️ by the AgiflowIO team
This server cannot be installed
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
Enables AI coding agents to generate standardized code using scaffolding templates, enforce architectural patterns, and validate outputs programmatically. Supports creating projects from boilerplates and adding features to existing codebases while maintaining team conventions.