Perform swipe gestures or hardware button presses
AI agents invoke idb_gesture to trigger actions in Xclaude Plugin. 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.
This tool triggers physical/simulated UI interactions (swipe gestures, hardware button presses) on an iOS simulator or device. These are external operations whose effects depend on arguments — navigating UI, triggering actions, simulating hardware inputs.
From the tool's definition Perform swipe gestures or hardware button presses
Attacks that exploit this kind of access
Perform swipe gestures or hardware button presses. It is categorised as a Execute tool in the Xclaude Plugin MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Xclaude Plugin MCP server in PolicyLayer and add a rule for idb_gesture: 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 Xclaude Plugin. Nothing to install.
idb_gesture 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 idb_gesture 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 idb_gesture. 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.
idb_gesture is provided by the Xclaude Plugin MCP server (conorluddy/xclaude-plugin). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
idb_gesture is one line of Xclaude Plugin's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →