get_port_settings
AI agents call get_port_settings to retrieve information from AC Infinity MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name contains the verb 'get', which is a quintessential Read operation. The server's stated capability to read sensor data and adjust states implies a distinction between read and write operations. With no description provided, confidence is reduced slightly, but contextual clues from the server's documented functionality strongly suggest this is a query/retrieve operation with no side effects.
From the tool's definition Tool name 'get_port_settings' combined with server context indicating it 'read[s] live sensor data' and 'adjust fan speeds or port states' suggests this retrieves configuration or status information about device ports without modifying them.
Attacks that exploit this kind of access
get_port_settings. It is categorised as a Read tool in the AC Infinity MCP MCP Server, which means it retrieves data without modifying state.
Register the AC Infinity MCP server in PolicyLayer and add a rule for get_port_settings: 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.
get_port_settings is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_port_settings 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 get_port_settings. 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.
get_port_settings 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 →