Shipvo
io.github.shipvo/shipvo · v0.0.6 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Open a React Native app in a simulated phone: read the screen, tap, type, set device state.
Source: https://github.com/shipvo/shipvo
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 110 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (kill_app). Require confirmation before the agent calls them. |
What was checked
- https://sim.shipvo.dev/mcp: answers without auth
- npm: @shipvo/mcp@0.0.6 (static checks only; code not executed)
Public tools: a11y_audit, a2ui_actions, a2ui_open, a2ui_send, app_activity, apply_update, approval_approve, approvals_list, arrange_apps, attach_session, audit_log, back, backup_phone, browser_back, browser_click, browser_close_tab, browser_open, browser_screenshot, browser_scroll, browser_snapshot, browser_tabs, browser_type, browser_wait_for, cancel_reminder, check_for_update, clear_schedule, clear_wakeup, close_panels, create_app, device_log
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-shipvo-shipvo-dcd5412e)