Register a peripheral on a GPIO pin (e.g. solenoid valve on pin 8 =
AI agents use farmbot_add_peripheral to create or update resources in Farmbot Agent — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Farmbot Agent environment.
The tool adds a new peripheral device configuration to the FarmBot system. While it modifies system state, registration is reversible (peripherals can be removed or updated), making it a Write action rather than Destructive or Execute.
From the tool's definition Tool name includes 'add' and description states 'Register a peripheral on a GPIO pin' – this creates a new hardware peripheral configuration that is reversibly stored.
Attacks that exploit this kind of access
Register a peripheral on a GPIO pin (e.g. solenoid valve on pin 8 =. It is categorised as a Write tool in the Farmbot Agent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Farmbot Agent MCP server in PolicyLayer and add a rule for farmbot_add_peripheral: 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_add_peripheral is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the farmbot_add_peripheral 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_add_peripheral. 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_add_peripheral 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 →