Web UX Evaluator
Web-QA-Agent is an MCP server implementation that enables AI assistants to evaluate web application user experiences through automated browser interactions. Built by Operative-Sh, it leverages Playwright for browser automation and integrates with Claude AI models to perform UX/UI analysis tasks. The server provides a specialized tool for assessing web interfaces, capturing console logs and network requests during evaluation, and generating detailed reports on usability issues and recommendations. This implementation is particularly valuable for UX researchers, web developers, and product teams who need AI-powered analysis of web application interfaces without manual testing.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- browser-automation
- Source
- PulseMCP
- Repository
- github.com/refreshdotdev/web-eval-agent
- Author type
- human
- Updated
- 2026-04-29
Use via MCP
Resolve Web UX Evaluator from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp --scope user for --scope project to commit it to .mcp.json.