Calibrate an axis by finding its total length (motion calibration, NOT camera). Moves the axis to both endpoints to determine the full range of motion. After calibration the axis length is written to firmware_config — verify with farmbot_get_firmware_config (movement_axis_nr_steps_*). Prereq: run...
AI agents invoke farmbot_calibrate 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 is an Execute-class tool because it triggers external hardware operations (axis movement) whose effects depend on arguments and cannot be easily reversed mid-operation. The severity is high because miscalibration could damage the robot (collision at endpoints) or render it non-functional until recalibrated. It is not Destructive because calibration is reversible by recalibrating with correct values.
From the tool's definition The tool performs hardware motion control—'Moves the axis to both endpoints to determine the full range of motion' and 'writes to firmware_config'. It triggers physical movement of the FarmBot gantry system and modifies persistent device configuration.
Attacks that exploit this kind of access
Calibrate an axis by finding its total length (motion calibration, NOT camera). Moves the axis to both endpoints to determine the full range of motion. After calibration the axis length is written to firmware_config — verify with farmbot_get_firmware_config (movement_axis_nr_steps_*). Prereq: run farmbot_find_home first so the bot knows where 0 is. For camera calibration use farmbot_execute_script({label:. 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_calibrate: 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_calibrate 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_calibrate 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_calibrate. 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_calibrate 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 →