AI agents invoke install_app_sim to trigger actions in Sl Test. 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.
Installing an app into a simulator is an external operation that modifies the simulator's state by deploying application code. It is not purely a data write (it executes/deploys code into a runtime environment), and while reversible (app can be uninstalled), the primary action is triggering an installation operation, placing it in the Execute category.
From the tool's definition Installs an app in an iOS simulator — requires simulatorUuid and appPath parameters
Attacks that exploit this kind of access
Installs an app in an iOS simulator. IMPORTANT: You MUST provide both the simulatorUuid and appPath parameters. Example: install_app_sim({ simulatorUuid:. It is categorised as a Execute tool in the Sl Test MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sl Test MCP server in PolicyLayer and add a rule for install_app_sim: 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 Sl Test. Nothing to install.
install_app_sim 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 install_app_sim 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 install_app_sim. 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.
install_app_sim is provided by the Sl Test MCP server (sampsonky/xcodebuildmcp). 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 →