AI agents call zte_get_port_forwards to retrieve information from Zte F680 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays configured port forwarding rules from the router. It performs a read-only query operation. However, severity is elevated to 'medium' rather than 'low' because port forwarding rules reveal network security architecture and access points, making this information valuable for reconnaissance if an attacker gains access to the router via a compromised AI agent.
From the tool's definition Tool name: zte_get_port_forwards; Description: 'Lista todas las reglas NAT/port forwarding configuradas' (Lists all configured NAT/port forwarding rules).
Attacks that exploit this kind of access
Lista todas las reglas NAT/port forwarding configuradas. It is categorised as a Read tool in the Zte F680 MCP Server, which means it retrieves data without modifying state.
Register the Zte F680 MCP server in PolicyLayer and add a rule for zte_get_port_forwards: 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 Zte F680. Nothing to install.
zte_get_port_forwards 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 zte_get_port_forwards 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 zte_get_port_forwards. 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.
zte_get_port_forwards is provided by the Zte F680 MCP server (picaresco/mcp-zte-f680). 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 →