AI agents invoke script 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 name 'script' strongly implies executing scripts or code. Given the server context (iOS Simulator control, browser-like interaction capabilities), a 'script' tool most likely runs arbitrary scripts within the simulator environment. The empty description lowers confidence, but 'script' in an automation/agent context almost universally means code execution.
From the tool's definition Tool name is 'script' on a server described as giving AI agents 'eyes and hands inside iOS Simulator apps' with ability to 'intercept network calls'. The description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access script 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 script:
{
"version": "1",
"default": "deny",
"tools": {
"script": {
"limits": [
{
"counter": "script_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}script 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.
script. 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 script: 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.
script 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 script 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 script. 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.
script 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.