farmbot_execute_script · Farmbot Agent MCP: Risk & Policy

WHAT IT DOES

What farmbot_execute_script does on Farmbot Agent

AI agents invoke farmbot_execute_script to trigger actions in Farmbot Agent. 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 IT NEEDS A POLICY

Why farmbot_execute_script needs a policy

This tool executes code (Lua scripts) on FarmBot hardware with real-world effects. Execution of scripts that control physical devices (gantry movement, emergency stops, calibration) carries significant risk if misused—an agent could trigger unintended hardware movements, disable safety systems, or corrupt device state.

From the tool's definition Tool description states 'Run a farmware (on-device script) by label' and server description confirms 'supports executing Lua scripts and core hardware commands like homing and emergency stops'. The tool executes arbitrary scripts on physical hardware.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

farmbot_execute_script Rate-limited

farmbot_execute_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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Farmbot Agent, so you can run agents against it safely.

FAQ

Questions about farmbot_execute_script

What does the farmbot_execute_script tool do? +

Run a farmware (on-device script) by label. This is the sole primitive for all setup/calibration/detection workflows — there are no separate. It is categorised as a Execute tool in the Farmbot Agent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on farmbot_execute_script? +

Register the Farmbot Agent MCP server in PolicyLayer and add a rule for farmbot_execute_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 Farmbot Agent. Nothing to install.

What risk level is farmbot_execute_script? +

farmbot_execute_script is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit farmbot_execute_script? +

Yes. Add a rate_limit block to the farmbot_execute_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.

How do I block farmbot_execute_script completely? +

Set action: deny in the PolicyLayer policy for farmbot_execute_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.

What MCP server provides farmbot_execute_script? +

farmbot_execute_script is provided by the Farmbot Agent MCP server (kieranklaassen/farmbot-agent-cli-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.