AI agents call zte_get_dmz 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 queries and retrieves DMZ status information from the router. It performs no side effects, makes no changes, executes no commands, and does not delete data. It is a straightforward information retrieval operation, fitting the 'Read' category with low severity due to the benign nature of reading network configuration state.
From the tool's definition Tool name 'zte_get_dmz' and description 'Devuelve el estado de la zona desmilitarizada (DMZ) y el host interno' (Returns the state of the demilitarized zone and the internal host) indicate a read-only operation that retrieves DMZ configuration status without…
Attacks that exploit this kind of access
Devuelve el estado de la zona desmilitarizada (DMZ) y el host interno. 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_dmz: 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_dmz 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_dmz 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_dmz. 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_dmz 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 →