Delete a firewall (must not be in use)
AI agents call delete_firewall to permanently remove resources in Hcloud — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a firewall is an irreversible action that removes infrastructure security controls. While the tool includes a guard (firewall must not be in use), the core function is destructive deletion. This ranks as Destructive (not Execute) because the outcome is guaranteed data/resource removal regardless of arguments.
From the tool's definition Tool name 'delete_firewall' combined with description 'Delete a firewall' explicitly performs irreversible deletion of a firewall resource. The constraint '(must not be in use)' does not change the destructive nature of the operation.
Attacks that exploit this kind of access
Delete a firewall (must not be in use). It is categorised as a Destructive tool in the Hcloud MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Hcloud MCP server in PolicyLayer and add a rule for delete_firewall: 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 Hcloud. Nothing to install.
delete_firewall 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 delete_firewall 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 delete_firewall. 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.
delete_firewall is provided by the Hcloud MCP server (xodus-co/hcloud-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 →