Independent preview-URL QA for coding agents. Playwright heuristics, pass/fail pack.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 4 tools
Each tool has a distinct role: qa_preview queues a run, qa_status polls its state, qa_get_report retrieves results, and qa_note closes a needs_review job. No overlap; boundaries are clear even from short descriptions.
All tools follow a consistent qa_verb_noun pattern (get_report, note, preview, status). The prefix unifies the API, and verb_noun structure is predictable across the entire set.
Four tools provide exactly the operations needed for a QA lifecycle: start, poll, retrieve, and close. This is well-scoped for a focused server—no bloat, no missing essentials.
The lifecycle covers preview → status → report → note, which handles the main QA flow. Minor gaps exist (no cancel/list jobs), but they are not critical for the core purpose and can be worked around.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
qa_get_reportqa_noteqa_previewqa_statusWebsite checker for AI coding agents. Measures your site in a real browser, with evidence.
Browser-based QA for AI-built software. Test pages with real browsers via agents.
Read-only web QA agent: scans a site in a real browser and returns evidence-backed findings
Preflight QA for AI-agent deliverables with structured verdicts and repair guidance.
Add one secure layer between your agents and this server.
