autopilot_explore
Automatically navigate the app, building a navigation graph of screens and transitions. Uses screen fingerprinting to avoid revisiting screens.
This record as markdown: /tools/alexgladkov-claude-in-mobile/autopilot-explore.md
What autopilot_explore does on Claude Mobile
AI agents invoke autopilot_explore 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.
Why autopilot_explore is rated High
This tool autonomously performs UI interactions on a mobile device/simulator, executing a sequence of actions (taps, navigations) across app screens without user intervention for each step. It can trigger arbitrary app functionality during exploration, potentially causing writes, purchases, or other side effects depending on the app being explored.
From the tool's definition Automatically navigate the app, building a navigation graph of screens and transitions
Attacks that exploit this kind of access
The rule that runs autopilot_explore safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Mobile, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For autopilot_explore, this is the rule to start with:
autopilot_explore stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Mobile, apply this rule, and every autopilot_explore call is checked against it from then on.
Questions about autopilot_explore
Automatically navigate the app, building a navigation graph of screens and transitions. Uses screen fingerprinting to avoid revisiting screens. It is categorised as a Execute tool in the Claude Mobile MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Mobile MCP server in PolicyLayer and add a rule for autopilot_explore: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude Mobile. Nothing to install.
autopilot_explore is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the autopilot_explore rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for autopilot_explore. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
autopilot_explore is provided by the Claude Mobile MCP server (alexgladkov/claude-in-mobile). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Claude Mobile, and thousands of servers like it.
Across the catalogue