execute_script

What execute_script does on ServiceNow MCP Server

AI agents invoke execute_script to trigger actions in ServiceNow MCP Server. 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.

Why execute_script is rated High

Server-side script execution is a classic Execute risk: the tool runs code whose effects depend entirely on the script argument provided. While not inherently Destructive (scripts could be read-only), the blast radius is high because malicious scripts could access, modify, or delete data within the ServiceNow instance, exfiltrate sensitive information, or trigger unintended business logic.

From the tool's definition Tool name is "execute_script" with description stating it "Execute[s] a server-side script on the ServiceNow instance (Background Script)." The explicit mention of executing scripts on a server instance indicates arbitrary code execution capability.

The rule that runs execute_script safely

PolicyLayer is an MCP gateway: it sits between your AI agents and ServiceNow MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For execute_script, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute_script": {
      "limits": [
        {
          "counter": "execute_script_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about execute_script