The reputation layer for AI skills, tools & agents

refreshdotdev/web-eval-agent

Score: 42.8 Rank #1084

An MCP server that autonomously evaluates web applications.

Overview

refreshdotdev/web-eval-agent is a Python MCP server licensed under Apache-2.0. An MCP server that autonomously evaluates web applications. Topics: debugging, debugging-tool, mcp, mcp-server, modelcontextprotocol, vibe-coding, vibe-testing, playwright, qa.

Ranked #1084 out of 25632 indexed tools.

In the top 5% of all indexed tools.

Has 1,238 GitHub stars.

Ecosystem

Python Apache-2.0
debuggingdebugging-toolmcpmcp-servermodelcontextprotocolvibe-codingvibe-testingplaywrightqa

Signal Breakdown

Stars 1,238
Freshness 1mo ago
Issue Health 41%
Contributors 7
Dependents 0
Forks 105
Description Good
License Apache-2.0

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Freshness high impact

Last commit was 33 days ago — a recent commit would boost your freshness score

Issue Health high impact

You have 17 open vs 12 closed issues — triaging stale issues improves health

Badge

AgentRank score for refreshdotdev/web-eval-agent
[![AgentRank](https://agentrank-ai.com/api/badge/tool/refreshdotdev--web-eval-agent)](https://agentrank-ai.com/tool/refreshdotdev--web-eval-agent)
<a href="https://agentrank-ai.com/tool/refreshdotdev--web-eval-agent"><img src="https://agentrank-ai.com/api/badge/tool/refreshdotdev--web-eval-agent" alt="AgentRank"></a>

Matched Queries

"mcp server""mcp-server"

From the README

# ⚠️ PROJECT HAS BEEN SUNSET ⚠️

## This project has been discontinued. We're building something new at [withrefresh.com](https://withrefresh.com)

---

# 🚀 operative.sh web-eval-agent MCP Server

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

## 🔥 Supercharge Your Debugging

[operative.sh](https://www.operative.sh/mcp)'s MCP Server launches a browser-use powered agent to autonomously execute and debug web apps directly in your code editor.

## ⚡ Features

- 🌐 **Navigate your webapp** using BrowserUse (2x faster with operative backend)
- 📊 **Capture network traffic** - requests are intelligently filtered and returned into the context window
- 🚨 **Collect console errors** - captures logs & errors
- 🤖 **Autonomous debugging** - the Cursor agent calls the web QA agent mcp server to test if the code it wrote works as epected end-to-end.

## 🧰 MCP Tool Reference

| Tool | Purpose |
|------|---------|
| `web_eval_agent` | 🤖 Automated UX evaluator that drives 
Read full README on GitHub →
Are you the maintainer? Claim this listing