MCP.so
Sign In
A

Ai Quality Gate

@mustafacagri

Repository

About Ai Quality Gate

πŸš€ Kill the Junior AI Era. πŸ€– Level up your AI code to Principal standards. No more sloppy lines or junior mistakes. Automated ESLint ✨ TypeScript πŸ”§ Prettier 🎨 SonarQube πŸ›‘οΈ Security πŸ”’ Complexity πŸ“Š in seconds. High-stakes quality, forced to ship only the best. βš‘πŸ† Goodbye, ba

#automation#opensource#typescript#ai#mcp#devtools#coding#cursor#codequality#mcp-server

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "ai-quality-gate": {
      "command": "npx",
      "args": [
        "-y",
        "ai-quality-gate"
      ]
    },
    "ai-quality-gate-custom-root": {
      "command": "npx",
      "args": [
        "-y",
        "ai-quality-gate"
      ],
      "env": {
        "PROJECT_ROOT": "/path/to/your/project"
      }
    },
    "ai-quality-gate-sonar": {
      "command": "npx",
      "args": [
        "-y",
        "ai-quality-gate"
      ],
      "env": {
        "PROJECT_ROOT": "/path/to/your/project",
        "SONAR_HOST_URL": "http://localhost:9000",
        "SONAR_TOKEN": "your_sonar_token",
        "SONAR_PROJECT_KEY": "your_project_key"
      }
    },
    "ai-quality-gate-global": {
      "command": "ai-quality-gate",
      "args": []
    }
  }
}

Tools

1

Run quality checks on code files and auto-fix deterministic issues. Phase 1 (Local, ~2-3s): TypeScript + ESLint + SonarJS (~60 rules) + AST fixers Phase 2 (Server, optional): Deep SonarQube analysis (only if configured) 🎯 Phase 1 is comprehensive - most users won't need Phase 2! Auto-fixes (ESLint + AST): - Curly braces on single-statement if (AST) - Single-expression arrow bodies where safe (AST) Code Quality Limits: - File: max 400 lines - Function: max 50 lines, max 5 params, max 4 depth, max 20 statements - Complexity: Cognitive max 15, Cyclomatic max 10 - Security: no-eval, no-new-func, no-implied-eval - Best Practices: eqeqeq, no-throw-literal, prefer-promise-reject-errors

Overview

What is Ai Quality Gate?

Ai Quality Gate is an MCP (Model Context Protocol) server that provides a quality_fix tool for AI-driven code quality automation. It runs a fast Phase 1 (ESLint with 627 bundled rules plus Prettier) and optionally a Phase 2 (SonarQube) to fix issues and report remaining problems. It is designed for MCP-capable editors like Cursor.

How to use Ai Quality Gate?

Install via npx -y ai-quality-gate or globally via npm i -g ai-quality-gate. Configure the server in your editor’s MCP settings (e.g., Cursor’s mcp.json). Add an AI rule that instructs the agent to call the quality_fix tool after every code change. Use the CLI flag --setup to interactively create a .quality-gate.yaml config file.

Key features of Ai Quality Gate

  • Hybrid quality gate: fast ESLint/Prettier phase always runs; optional SonarQube phase.
  • Bundles 627 static analysis rules from SonarJS, Unicorn, TypeScript-ESLint, and more.
  • Auto-fixes ~100+ ESLint issues including unused imports and var-to-const/let.
  • Customizable via YAML/JSON config files and environment variables.
  • Supports custom regex-based rules for project-specific checks.
  • Validates i18n locale JSON files for key consistency.

Use cases of Ai Quality Gate

  • Ensure AI-generated code meets project quality standards before reporting completion.
  • Automate code review in CI/CD pipelines with optional SonarQube integration.
  • Enforce consistent coding style and best practices across a team repository.
  • Quickly fix common issues like unused

Comments

Basic information

Category

Developer Tools

Transports

stdio

Author

mustafacagri

Submitted by

Cagri Guven

More Developer Tools MCP servers

AptiBuild AI β€” Career Intelligence

ParklandBuilds

AptiBuild AI β€” Career Intelligence MCP Server Structured career decision scaffolding for AI agents. Provides personality-conditioned business idea generation, official BLS OEWS wage data, FRED labor market signals, and

CodeSentinel

icohangar-ops

Codebase health as MCP tools: dead code, circular dependencies, coupling, architectural drift.

Mobbin

Mobbin

Mobbin MCP connects your AI agents to 600,000+ real product screens, so what they build starts with what already works.

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

1

TaskerArmy Agent

TaskerArmy

Ask Claude or ChatGPT what Shopify theme optimization tasks are pending on your store, a remote MCP server for TaskerArmy Agent accounts.