# autopilot

AI Test Autopilot. explore: auto-navigate app and build navigation graph. generate: create test scenarios from exploration. heal: self-heal broken test selectors. status: exploration status. tests: list/get generated tests.

Agent View of the PolicyLayer registry record for `autopilot`. HTML page: https://policylayer.com/tools/alexgladkov-claude-in-mobile/autopilot

## Facts

- Tool: `autopilot`
- Server: Claude Mobile (`alexgladkov/claude-in-mobile`) — https://policylayer.com/tools/alexgladkov-claude-in-mobile.md
- Homepage: https://github.com/AlexGladkov/claude-in-mobile
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "autopilot",
    "arguments": {}
  }
}
```

## Why autopilot is rated High

This is an Execute category tool because it runs automated sequences that trigger external operations on the mobile device (app navigation, UI interactions, test execution). While individual operations like reading state might be Read-level, the autopilot's core function is to automatically execute navigation and test scenarios whose side effects (app state changes, data modifications) depend on generated test logic.

From the tool's own definition: "The tool performs 'auto-navigate app', 'create test scenarios', 'self-heal broken test selectors', and 'exploration status' operations."

## Use case

AI agents invoke autopilot to trigger actions in Claude Mobile. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Claude Mobile:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "autopilot": {
      "limits": [
        {
          "counter": "autopilot_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Claude Mobile (197)

- `browser_clear_session` — Destructive — https://policylayer.com/tools/alexgladkov-claude-in-mobile/browser-clear-session.md
- `debug_remove_break` — Destructive — https://policylayer.com/tools/alexgladkov-claude-in-mobile/debug-remove-break.md
- `network_proxy` — Destructive — https://policylayer.com/tools/alexgladkov-claude-in-mobile/network-proxy.md
- `permission_reset` — Destructive — https://policylayer.com/tools/alexgladkov-claude-in-mobile/permission-reset.md
- `permission_revoke` — Destructive — https://policylayer.com/tools/alexgladkov-claude-in-mobile/permission-revoke.md
- `recorder` — Destructive — https://policylayer.com/tools/alexgladkov-claude-in-mobile/recorder.md
- `recorder_delete` — Destructive — https://policylayer.com/tools/alexgladkov-claude-in-mobile/recorder-delete.md
- `recorder_remove_step` — Destructive — https://policylayer.com/tools/alexgladkov-claude-in-mobile/recorder-remove-step.md
- `repl_kill` — Destructive — https://policylayer.com/tools/alexgladkov-claude-in-mobile/repl-kill.md
- `rustore_discard` — Destructive — https://policylayer.com/tools/alexgladkov-claude-in-mobile/rustore-discard.md
- `sensor_battery` — Destructive — https://policylayer.com/tools/alexgladkov-claude-in-mobile/sensor-battery.md
- `store_discard` — Destructive — https://policylayer.com/tools/alexgladkov-claude-in-mobile/store-discard.md
- `sync_destroy` — Destructive — https://policylayer.com/tools/alexgladkov-claude-in-mobile/sync-destroy.md
- `system_clear_logs` — Destructive — https://policylayer.com/tools/alexgladkov-claude-in-mobile/system-clear-logs.md
- `visual` — Destructive — https://policylayer.com/tools/alexgladkov-claude-in-mobile/visual.md
- `visual_delete` — Destructive — https://policylayer.com/tools/alexgladkov-claude-in-mobile/visual-delete.md
- `app` — Execute — https://policylayer.com/tools/alexgladkov-claude-in-mobile/app.md
- `app_install` — Execute — https://policylayer.com/tools/alexgladkov-claude-in-mobile/app-install.md
- `app_launch` — Execute — https://policylayer.com/tools/alexgladkov-claude-in-mobile/app-launch.md
- `app_restart` — Execute — https://policylayer.com/tools/alexgladkov-claude-in-mobile/app-restart.md
- `app_stop` — Execute — https://policylayer.com/tools/alexgladkov-claude-in-mobile/app-stop.md
- `appstore_build` — Execute — https://policylayer.com/tools/alexgladkov-claude-in-mobile/appstore-build.md
- `appstore_submit` — Execute — https://policylayer.com/tools/alexgladkov-claude-in-mobile/appstore-submit.md
- `appstore_upload` — Execute — https://policylayer.com/tools/alexgladkov-claude-in-mobile/appstore-upload.md
- `autopilot_explore` — Execute — https://policylayer.com/tools/alexgladkov-claude-in-mobile/autopilot-explore.md
- `autopilot_heal` — Execute — https://policylayer.com/tools/alexgladkov-claude-in-mobile/autopilot-heal.md
- `browser` — Execute — https://policylayer.com/tools/alexgladkov-claude-in-mobile/browser.md
- `browser_click` — Execute — https://policylayer.com/tools/alexgladkov-claude-in-mobile/browser-click.md
- `browser_close` — Execute — https://policylayer.com/tools/alexgladkov-claude-in-mobile/browser-close.md
- `browser_evaluate` — Execute — https://policylayer.com/tools/alexgladkov-claude-in-mobile/browser-evaluate.md
- …and 167 more: https://policylayer.com/tools/alexgladkov-claude-in-mobile.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=alexgladkov-claude-in-mobile · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/alexgladkov-claude-in-mobile