MCP Catalogs
Homeaicode-toolkit screenshot

aicode-toolkit

by AgiFlow·156·Score 48

MCP server toolkit providing project scaffolding, code guidance, and design system discovery for AI agents.

developer-toolsai-llmproductivity
22
Forks
2
Open issues
this month
Last commit
2d ago
Indexed

Overview

The AI Code Toolkit is a comprehensive MCP server solution that helps AI coding agents work reliably with repositories of any size. It provides project scaffolding through templates, file-level design guidance, rule-based code reviews, and design system discovery tools. The toolkit consists of multiple MCP servers including scaffold-mcp for boilerplate generation, architect-mcp for pattern guidance and code review, and style-system for theme and component discovery.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Generate new projects and features from predefined templates
you:Apply consistent design patterns and rules to code changes
you:Discover and implement UI themes, CSS classes, and components
you:Which AI agents support this MCP server?
you:Can I create custom templates?

When to choose this

Choose this toolkit when working with multiple coding agents to maintain consistency across projects or when implementing standardized scaffolding and design patterns.

When NOT to choose this

Avoid if you need a simple solution for small projects or if you're concerned about vendor lock-in with the AgiFlow-specific MCP servers.

Tools this server exposes

12 tools extracted from the README
  • list-boilerplates

    Lists available boilerplates for project initialization

  • use-boilerplate

    Uses a specified boilerplate to initialize a project

  • list-scaffolding-methods

    Lists available scaffolding methods for adding features

  • use-scaffold-method

    Uses a specified scaffolding method to add features

  • get-file-design-pattern

    Returns design patterns for a specific file before editing

  • review-code-change

    Reviews code changes against defined rules

  • list_themes

    Lists available design themes

  • get_css_classes

    Returns CSS classes available in the current theme

  • get_component_visual

    Returns visual representation of a component

  • list_shared_components

    Lists shared components in the project

  • list_app_components

    Lists application-specific components

  • add-design-pattern

    Adds a new design pattern to the project

Comparable tools

github-copilot-mcpcursor-mcpstandard-mcp

Installation

Installation

  1. Install via npm for your project:
npx @agiflowai/aicode-toolkit init
  1. Configure MCP in your AI agent settings. For Claude Code, add to .mcp.json:
{
  "mcpServers": {
    "scaffold-mcp": {
      "command": "npx",
      "args": ["-y", "@agiflowai/scaffold-mcp", "mcp-serve", "--admin-enable"]
    },
    "architect-mcp": {
      "command": "npx",
      "args": ["-y", "@agiflowai/architect-mcp", "mcp-serve", "--admin-enable"]
    },
    "style-system": {
      "command": "npx",
      "args": ["-y", "@agiflowai/style-system", "mcp-serve"]
    }
  }
}

FAQ

Which AI agents support this MCP server?
The toolkit supports Claude Code, Cursor, Gemini CLI, Codex CLI, GitHub Copilot, and Windsurf (planned).
Can I create custom templates?
Yes, use the admin tools like generate-boilerplate and add-design-pattern to create custom templates and rules.

Compare aicode-toolkit with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.