DebuggAI

Provides zero-configuration end-to-end testing for web applications by creating secure tunnels to local development servers and sp

debugg-ai 81 ↓ 28k
Claude CodeClaude DesktopGeneric
View source ↗

This MCP server provides zero-configuration AI-managed end-to-end testing for web applications by integrating with the DebuggAI platform to automatically generate and execute UI tests using AI agents. Built by Quinn Osha using TypeScript with ngrok tunneling, axios for API communication, and the Model Context Protocol SDK, it creates secure tunnels to local development servers, spawns AI testing agents that interact with web interfaces through natural language descriptions, and returns detailed test results including execution recordings and final screenshots. The implementation handles the complete testing lifecycle from tunnel creation to AI agent coordination, with support for Docker deployment and configurable environment variables for repository context, making it valuable for developers who need automated UI testing without writing test scripts, continuous integration workflows requiring AI-driven quality assurance, and scenarios where traditional testing approaches are insufficient for dynamic user interfaces.

Source

Repository: https://github.com/debugg-ai/debugg-ai-mcp

Maintain DebuggAI?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

DebuggAI on getagentictools
[![DebuggAI on getagentictools](https://getagentictools.com/badge/mcp/debugg-ai-debugg-ai-mcp.svg)](https://getagentictools.com/mcp/debugg-ai-debugg-ai-mcp?ref=badge)