Move the FarmBot gantry to a position in the garden. Coordinates are in millimeters from the home position (0,0,0). - X: along the length of the bed (0 to ~3000mm for standard, ~6000mm for XL) - Y: across the width of the bed (0 to ~1500mm for standard, ~3000mm for XL) - Z: height (0 = top, negat...
AI agents invoke farmbot_move 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 triggers physical hardware movement of a robotic gantry system. It executes real-world actions with physical consequences (moving machinery into soil, potentially damaging plants, hardware, or the device itself). Misuse could cause physical damage — e.g., driving the gantry into an obstacle or into the soil at an unsafe depth.
From the tool's definition Move the FarmBot gantry to a position in the garden... enables AI agents to manage gardening tasks through tools like gantry movement
Attacks that exploit this kind of access
Move the FarmBot gantry to a position in the garden. Coordinates are in millimeters from the home position (0,0,0). - X: along the length of the bed (0 to ~3000mm for standard, ~6000mm for XL) - Y: across the width of the bed (0 to ~1500mm for standard, ~3000mm for XL) - Z: height (0 = top, negative = into soil, e.g. -50 for planting depth) Set relative=true to move relative to current position instead of absolute. Returns the target position after movement completes. 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_move: 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_move 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_move 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_move. 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_move 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →