Execute Lua code directly on the FarmBot device. This is an escape hatch for advanced operations not covered by other tools. The FarmBot Lua runtime includes functions for movement, pins, photos, and more. Example: move{x=100, y=200, z=0} Example: water(plant_id) Example: take_photo() WARNING: Th...
AI agents invoke farmbot_lua 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.
This tool executes arbitrary Lua scripts on physical hardware (FarmBot device), making it Execute category. The severity is critical because: (1) it enables arbitrary code execution without sandboxing, (2) the device controls physical machinery (gantry movement, watering, etc.) whose malfunction could damage crops or equipment, (3) an AI agent with unsupervised access could cause unintended harm to the garden…
From the tool's definition Execute Lua code directly on the FarmBot device. This is an escape hatch for advanced operations. Example: move{x=100, y=200, z=0}, water(plant_id), take_photo(). WARNING: This executes arbitrary code on the device.
Attacks that exploit this kind of access
Execute Lua code directly on the FarmBot device. This is an escape hatch for advanced operations not covered by other tools. The FarmBot Lua runtime includes functions for movement, pins, photos, and more. Example: move{x=100, y=200, z=0} Example: water(plant_id) Example: take_photo() WARNING: This executes arbitrary code on the device. Use with caution. 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.
Register the Farmbot Agent MCP server in PolicyLayer and add a rule for farmbot_lua: 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.
farmbot_lua 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 farmbot_lua 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 farmbot_lua. 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.
farmbot_lua 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.
farmbot_lua is one line of Farmbot Agent's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →