AI agents invoke ui_tap 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 UI interactions (taps) on a running iOS Simulator, which constitutes executing browser/application actions whose effects depend on what element is tapped. The impact varies widely based on what is tapped (e.g., could trigger purchases, deletions, or other significant actions within the app), making it an Execute-category tool with medium severity.
From the tool's definition Tap on the screen at specific coordinates in the iOS Simulator. Use this to tap buttons, icons, or any interactive element.
Attacks that exploit this kind of access
Tap on the screen at specific coordinates in the iOS Simulator. Use this to tap buttons, icons, or any interactive element. 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_tap: 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_tap 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_tap 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_tap. 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_tap 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →