set_port_on
AI agents use set_port_on to create or update resources in AC Infinity MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AC Infinity MCP environment.
The tool changes the state of a port (likely enabling/disabling power to connected devices like fans or humidifiers), which is a Write-category action—it creates or modifies system state. While reversible (can be turned off again with set_port_off), incorrect use could disrupt climate control in a growing environment.
From the tool's definition Tool name 'set_port_on' indicates a state-changing action on physical ports controlled by AC Infinity devices (fan controllers).
Attacks that exploit this kind of access
set_port_on. It is categorised as a Write tool in the AC Infinity MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AC Infinity MCP server in PolicyLayer and add a rule for set_port_on: 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 AC Infinity MCP. Nothing to install.
set_port_on 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 set_port_on 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 set_port_on. 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.
set_port_on is provided by the AC Infinity MCP server (ober37/ac-infinity-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 →