AI agents invoke ui_swipe to trigger actions in Shotter. 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 an external UI interaction (swipe gesture) on the iOS Simulator, causing side effects that depend on the arguments (direction, coordinates, target element). It is not a simple read, and while it doesn't destroy data or move money, it executes an action in an external environment, fitting the Execute category.
From the tool's definition "Perform a swipe gesture on the iOS Simulator screen" and "scroll content or perform swipe actions"
Attacks that exploit this kind of access
Perform a swipe gesture on the iOS Simulator screen. Use this to scroll content or perform swipe actions. It is categorised as a Execute tool in the Shotter MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Shotter MCP server in PolicyLayer and add a rule for ui_swipe: 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 Shotter. Nothing to install.
ui_swipe 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 ui_swipe 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 ui_swipe. 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.
ui_swipe is provided by the Shotter MCP server (nathanstitt/shotter). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
ui_swipe is one line of Shotter'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 →