AI agents invoke sim_control to trigger actions in Pepper. 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.
The server description indicates control over iOS Simulator (tapping buttons, viewing screens, intercepting network calls). 'sim_control' most likely provides simulator control actions (launch, terminate, interact), which constitutes executing external operations. The empty description lowers confidence, but the server context and naming strongly imply Execute-level capabilities.
From the tool's definition Tool name 'sim_control' on a server described as giving AI agents 'eyes and hands inside iOS Simulator apps, enabling them to view screens, tap buttons, inspect objects, and intercept network calls'.
Documented attack patterns abuse exactly the kind of access sim_control gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pepper, and nothing reaches the server without passing your rules. This is the rule we recommend for sim_control:
{
"version": "1",
"default": "deny",
"tools": {
"sim_control": {
"limits": [
{
"counter": "sim_control_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}sim_control stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
sim_control. It is categorised as a Execute tool in the Pepper MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pepper MCP server in PolicyLayer and add a rule for sim_control: 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 Pepper. Nothing to install.
sim_control 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 sim_control 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 sim_control. 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.
sim_control is provided by the Pepper MCP server (skwallace36/pepper). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Pepper tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
3 Pepper tools catalogued and risk-classified — across an index of 42,500+ MCP servers.