AI agents invoke AppleScript-Tool to trigger actions in Android. 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.
AppleScript-Tool triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
Execute AppleScript commands. It is categorised as a Execute tool in the Android MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Android MCP server in PolicyLayer and add a rule for AppleScript-Tool: 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 Android. Nothing to install.
AppleScript-Tool 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 AppleScript-Tool 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 AppleScript-Tool. 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.
AppleScript-Tool is provided by the Android MCP server (tomdwipo/agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.