web-eval-agent

Autonomous web app evaluator using MCP. Tests & scores web applications.

1,100
87
# 🚀 operative.sh web-eval-agent MCP Server

> *Let the coding agent debug itself, you've got better things to do.*

![Demo](./demo.gif)

## 🔥 Supercharge Your Debugging with Autonomous Web App Evaluation

The `operative.sh` [Model Context Protocol (MCP) Server](https://www.operative.sh/mcp) empowers your coding agents to autonomously execute and debug web applications directly from your code editor.  It leverages a browser-use powered agent, freeing you from tedious manual testing.

## ⚡ Key Features

*   **🌐 Browser-Powered Navigation:**  Utilizes BrowserUse for efficient web application navigation (2x faster with the operative backend).
*   **📊 Intelligent Network Traffic Capture:**  Captures and filters relevant network requests, providing valuable context within the agent's window.
*   **🚨 Comprehensive Console Error Collection:**  Captures console logs and errors, aiding in rapid issue identification.
*   **🤖 Autonomous Debugging Workflow:**  Enables your coding agent (e.g., Cursor) to call the `web_eval_agent` MCP server to automatically test and validate code changes end-to-end.

## 🧰 MCP Tool Reference

This MCP server provides the following tools for use by your coding agent:

| Tool                | Purpose

Repository

OP
Operative-Sh

Operative-Sh/web-eval-agent

Created

April 1, 2025

Updated

July 7, 2025

Language

Python

Category

Developer Tools