AI agents call firewall_addrgrp_delete to permanently remove resources in FortiOS 7 6 X MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The 'delete' verb indicates this tool irreversibly removes configuration data (firewall address groups). This cannot be undone and represents a destructive operation. Severity is high rather than critical because the blast radius is limited to firewall address group configuration rather than affecting live traffic or causing widespread system compromise, but an AI agent misusing this could remove critical network…
From the tool's definition Tool name 'firewall_addrgrp_delete' explicitly contains 'delete', indicating irreversible removal of firewall address group data. The context shows this is part of a FortiOS REST API MCP server that exposes firewall management operations.
Documented attack patterns abuse exactly the kind of access firewall_addrgrp_delete gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and FortiOS 7 6 X MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for firewall_addrgrp_delete:
{
"version": "1",
"default": "deny",
"hide": [
"firewall_addrgrp_delete"
]
}firewall_addrgrp_delete disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
firewall_addrgrp_delete. It is categorised as a Destructive tool in the FortiOS 7 6 X MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the FortiOS 7 6 X MCP Server MCP server in PolicyLayer and add a rule for firewall_addrgrp_delete: 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 FortiOS 7 6 X MCP Server. Nothing to install.
firewall_addrgrp_delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the firewall_addrgrp_delete 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 firewall_addrgrp_delete. 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.
firewall_addrgrp_delete is provided by the FortiOS 7 6 X MCP Server MCP server (paoloamato2/fortinet-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from FortiOS 7 6 X MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
240 FortiOS 7 6 X MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.