AI Code Toolkit
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 ma
What is AI Code Toolkit?
AI Code Toolkit is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables ai coding agents to generate standardized code using scaffolding templates, enforce architectural patterns, and validate outputs programmatically. supports creating projects from boilerplates ...
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 ma
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables AI coding agents to generate standardized code using
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx ai-code-toolkitConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use AI Code Toolkit
AI Code Toolkit is a suite of MCP servers (scaffold-mcp, architect-mcp, and style-system) that gives AI coding agents access to organizational scaffolding templates, architectural design patterns, and design system tokens — enabling them to generate standardized, company-consistent code rather than improvising structure from scratch. It enforces conventions through YAML-defined rules and validates outputs programmatically, making it especially valuable for teams doing high-velocity 'vibe coding' who need guardrails to keep AI-generated code maintainable.
Prerequisites
- Node.js 18 or newer installed
- npx available (comes with Node.js)
- An MCP-compatible client such as Claude Code, Cursor, or Gemini CLI
- Optional: project templates already configured in scaffold.yaml, architect.yaml, and RULES.yaml for your team's conventions
Initialize AI Code Toolkit in your project
Run the init command in your project root. For a new project, add --name and --project-type flags. This sets up the required YAML configuration files.
npx @agiflowai/aicode-toolkit init
# Or for a new project:
npx @agiflowai/aicode-toolkit init --name my-app --project-type monolithReview and customize the generated YAML files
Three YAML files control the toolkit's behavior: scaffold.yaml defines boilerplate configurations, architect.yaml defines file-level patterns, and RULES.yaml sets code review standards. Edit them to match your team's conventions.
Configure your MCP client with the three servers
Add scaffold-mcp, architect-mcp, and style-system to your .mcp.json or claude_desktop_config.json. Use --admin-enable for template authoring capabilities.
Verify available boilerplates and scaffolding methods
Ask your AI assistant to list available boilerplates to confirm the servers are connected and your YAML definitions are loaded correctly.
Generate a project or feature from a boilerplate
Once connected, instruct the AI to scaffold a new feature or project using the templates defined in scaffold.yaml. The agent selects the relevant boilerplate and generates conformant code.
AI Code Toolkit Examples
Client configuration
Claude Code .mcp.json configuration with all three AI Code Toolkit servers. The --admin-enable flag allows template authoring in addition to template consumption.
{
"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"]
}
}
}Prompts to try
Example prompts that use AI Code Toolkit's scaffolding and architectural guidance tools.
- "List all available boilerplates and tell me which one is best for a Next.js + Drizzle project"
- "Scaffold a new feature called 'user-authentication' using the Next.js boilerplate"
- "Get the file design pattern for the components/Button.tsx file and show me what conventions I should follow"
- "Review the code changes in my last commit against the team's RULES.yaml standards"
- "List available CSS classes from the style system for building a responsive card layout"Troubleshooting AI Code Toolkit
list-boilerplates returns empty results
Ensure scaffold.yaml exists in the project root and contains at least one boilerplate definition. Run 'npx @agiflowai/aicode-toolkit init' to generate starter YAML files if they are missing.
scaffold-mcp or architect-mcp fails to start with ENOENT
Verify Node.js 18+ is installed ('node --version'). Clear the npx cache with 'npx clear-npx-cache' and retry. If the issue persists, install the packages globally: npm install -g @agiflowai/scaffold-mcp @agiflowai/architect-mcp.
Code review tool returns no violations even for non-conformant code
The review-code-change tool requires --review-tool flag to be added to architect-mcp's args. Add it to the args array: [..., "--review-tool"]. Also ensure RULES.yaml contains explicit, machine-checkable rules.
Frequently Asked Questions about AI Code Toolkit
What is AI Code Toolkit?
AI Code Toolkit is a Model Context Protocol (MCP) server that 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 ma It connects AI assistants to external tools and data sources through a standardized interface.
How do I install AI Code Toolkit?
Follow the installation instructions on the AI Code Toolkit GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with AI Code Toolkit?
AI Code Toolkit works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is AI Code Toolkit free to use?
Yes, AI Code Toolkit is open source and available under the AGPL 3.0 license. You can use it freely in both personal and commercial projects.
AI Code Toolkit Alternatives — Similar Coding Agents Servers
Looking for alternatives to AI Code Toolkit? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up AI Code Toolkit 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 AI Code Toolkit?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.