execute_batch

What execute_batch does on Openhab

AI agents invoke execute_batch to trigger actions in Openhab. 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_batch is rated High

This tool allows execution of arbitrary commands in parallel without apparent constraints. In a home automation context, executing multiple commands simultaneously could trigger unintended device actions (e.g., unlocking doors, turning off critical systems, disabling security). The ability to execute batches amplifies the risk compared to single-command execution.

From the tool's definition Tool named 'execute_batch' with description stating 'Execute multiple commands in parallel.' The verb 'execute' combined with 'commands' and the context of an OpenHAB automation/control system indicates arbitrary command execution.

The rule that runs execute_batch safely

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

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

Questions about execute_batch