ZaneL1u / remote-webview-debugger

Let AI agents debug the WebViews inside your app and your H5 pages — on real users' phones, over MCP.

Why this job: works in the areas we cover, but does not say which job it does

What it does

Device-first. A device (one app install or browser) has many pages; one API key and one MCP server reach every device. The agent follows navigations and newly opened WebViews and sees a cross-page timeline.
Agent tools. Accessibility snapshots with element refs (Playwright's aria snapshot), find, click, fill, type, press, select, hover, scroll, drag, navigate, evaluate, console, network with bodies, storage, screenshots (native bridge or DOM),
Consent and control. On-device approval with levels (observe / interact / advanced), optional auto-approve, screen lock while the agent operates, take over / hand back / end, confirmation for sensitive actions (data-rwd-confirm).
Privacy. Password fields, data-rwd-mask and configurable selectors / patterns are masked in snapshots, screenshots, console and network data. The audit log records who did what, without page content.
Operations. Members and roles, API keys with level / expiry / IP allowlist, device tokens, invites by QR code, quotas, live console over SSE, Prometheus metrics.

More: download files, languages, topics and project record