CORBAT

CORBAT MCP injects your team’s coding standards into AI-assisted code generation, ensuring AI-created code aligns with your patterns before production. It enforces quality, architecture, and security rules at the source of generation, reducing review iterations and patching the AI’s output early in the workflow.

How to use

You integrate CORBAT MCP with your existing MCP client by adding a server configuration that runs locally. CORBAT MCP applies your guardrails as the AI generates code, so the AI is already aware of your standards during the first drafting step. This enables you to ship production-ready code with fewer follow-ups.

How to install

Prerequisites: you need Node.js and npm installed on your machine.

1. Add CORBAT MCP to your MCP config using the standard local MCP runner.

2. Use interactive setup to detect your stack and generate a default CORBAT configuration.

3. Optionally customize the configuration in the generated file to tailor rules and architecture guidelines to your project.

Option 1: Interactive Setup

npx corbat-init

Detects your stack and generates a `.corbat.json` with sensible defaults.

Option 2: Manual Configuration

Create `.corbat.json` in your project root:

```json
{
  "profile": "java-spring-backend",
  "architecture": {
    "pattern": "hexagonal",
    "layers": ["domain", "application", "infrastructure", "api"]
  },
  "quality": {
    "maxMethodLines": 20,
    "maxClassLines": 200,
    "minCoverage": 80
  },
  "rules": {
    "always": [
      "Use records for DTOs",
      "Prefer Optional over null"
    ],
    "never": [
      "Use field injection",
      "Catch generic Exception"
    ]
  }
}

Option 3: Use a Template Browse 14 ready-to-use templates for Java, Python, Node.js, React, Go, Rust, and more.

## Additional setup notes

Important: CORBAT MCP auto-detects your stack and applies the right standards. It runs locally and adds about 50 milliseconds to detect your stack, after which it simply provides context for the AI.

You can override any rule by editing the `.corbat.json` file to suit your team’s needs.

## Examples of what you gain with CORBAT MCP

The following demonstrates how CORBAT MCP shapes code to meet governance and architectural goals while preserving readability and testability.

// Example: Before CORBAT MCP (simplified) class UserService { private users: Map<string, User> = new Map();

register(name: string, email: string, password: string) { if (!name || !email || !password) throw new Error('Invalid input'); const user = { id: crypto.randomUUID(), name, email, password }; this.users.set(user.id, user); return user; } }

// Example: After CORBAT MCP enforces guards (simplified) interface UserRepository { save(user: User): Promise<void>; findByEmail(email: string): Promise<User | null>; }

class EmailAlreadyExistsError extends Error { constructor(email: string) { super(Email already registered: ${email}); } }

class RegisterUserUseCase { constructor( private readonly repository: UserRepository, private readonly hasher: PasswordHasher ) {}

async execute(input: RegisterUserInput): Promise<User> { const existing = await this.repository.findByEmail(input.email); if (existing) throw new EmailAlreadyExistsError(input.email);

const user = User.create({ ...input, password: await this.hasher.hash(input.password) });
await this.repository.save(user);
return user;

} }