{"id":"web-eval-agent","name":"Web Eval Agent","homepage":"https://withrefresh.com","repo_url":"https://github.com/refreshdotdev/web-eval-agent","category":"testing-qa","subcategories":["browser-testing","automated-qa","web-evaluation"],"tags":["browser","testing","mcp","browser-use","playwright","ux-evaluation","network-monitoring","sunsetted"],"what_it_does":"A now-sunsetted MCP server that autonomously evaluated web applications by driving a browser agent through user-specified tasks, capturing screenshots, console logs, and network traffic, then returning a rich UX report to the calling AI agent.","use_cases":["Autonomous end-to-end testing of web apps from within Cursor, Cline, or Windsurf","Letting coding agents self-test their own implementations before committing","Capturing network traffic and console errors during automated UI walkthroughs","Browser session state setup (login/auth) for subsequent automated test runs"],"not_for":["New projects — this tool is sunsetted and no longer maintained","Production CI/CD pipelines requiring long-term stability","Teams needing enterprise support or SLA guarantees"],"best_when":"Historically best for quick autonomous UX evaluation loops within AI coding editors — but the project is discontinued. Evaluate alternatives instead.","avoid_when":"Starting new integrations — the project is sunsetted. Use vibetest-use or a maintained browser testing MCP instead.","alternatives":["vibetest-use","web-agent-protocol","playwright-mcp","browserbase","operative"],"af_score":53.8,"security_score":50.0,"reliability_score":null,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":"latest","last_evaluated":"2026-03-01T09:50:06.401384+00:00","performance":{"latency_p50_ms":null,"latency_p99_ms":null,"uptime_sla_percent":null,"rate_limits":null,"data_source":"llm_estimated","measured_on":null}}