Agent-driven web QA: scan a site, auto-generate + run E2E test flows, read results.
siteglass.io's web-QA loop as MCP tools, so an AI coding agent can test the app it just built — register → verify → scan → generate flows → run → read results — autonomously, no human signup. Auth is automatic (creates + caches an API key at ); set to use your own. The first scan per site is free; after that, scans (2 credits) and flow runs (1 credit) draw from a prepaid balance topped up in USD…
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.
siteglass.io's web-QA loop as MCP tools, so an AI coding agent can test the app it just built — register → verify → scan → generate flows → run → read results — autonomously, no human signup. Auth is automatic (creates + caches an API key at ); set to use your own. The first scan per site is free; after that, scans (2 credits) and flow runs (1 credit) draw from a prepaid balance topped up in USD over Bitcoin Lightning. Cursor / Claude Desktop / Windsurf — add to the MCP config OpenClaw — add to…