autopilot_generate
Generate test scenarios from exploration data. Creates flow_run-compatible test steps for all unique paths.
This record as markdown: /tools/alexgladkov-claude-in-mobile/autopilot-generate.md
What autopilot_generate does on Claude Mobile
AI agents use autopilot_generate to create or update resources in Claude Mobile, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Mobile environment.
Why autopilot_generate is rated Medium
The tool generates test scenarios and creates test steps based on exploration data. This is a Write operation because it creates new data structures (test steps) that can be used by other tools. While the output is test data rather than production data, misuse could result in malformed test definitions that break testing workflows or consume resources.
From the tool's definition Tool description states it 'Creates flow_run-compatible test steps', indicating generation and creation of new data artifacts (test scenarios/steps).
Attacks that exploit this kind of access
The rule that runs autopilot_generate 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_generate, this is the rule to start with:
autopilot_generate stays usable, but capped: an agent stuck in a loop can't make hundreds of changes 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_generate call is checked against it from then on.
Questions about autopilot_generate
Generate test scenarios from exploration data. Creates flow_run-compatible test steps for all unique paths. It is categorised as a Write tool in the Claude Mobile MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Mobile MCP server in PolicyLayer and add a rule for autopilot_generate: 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_generate is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the autopilot_generate 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_generate. 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_generate 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.
This server
Across the catalogue