AI agents use zte_modify_port_forward to create or update resources in Zte F680 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zte F680 environment.
The tool name indicates modification of port forwarding rules on a GPON router. Port forwarding changes are reversible (Write category), but carry high severity since misconfiguration can expose internal network services to the internet or disrupt network connectivity. Description is empty, so confidence is reduced, but the naming pattern and server context make the classification clear.
From the tool's definition Tool name 'zte_modify_port_forward' combined with sibling tools 'zte_add_port_forward' and 'zte_delete_port_forward' on a router management server
Attacks that exploit this kind of access
zte_modify_port_forward. It is categorised as a Write tool in the Zte F680 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zte F680 MCP server in PolicyLayer and add a rule for zte_modify_port_forward: 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_modify_port_forward 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 zte_modify_port_forward 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_modify_port_forward. 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_modify_port_forward 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 →