AI agents use apply_firewall_to_resources to create or update resources in Hcloud — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Hcloud environment.
The tool creates or modifies firewall associations on cloud servers, which is a Write operation (reversible configuration change). While it affects security posture and has significant blast radius if misapplied to wrong resources, it is not Destructive (not irreversible), Execute (not running arbitrary code), or Financial.
From the tool's definition apply_firewall_to_resources applies a firewall to servers or resources via label selector. This modifies network security policies on cloud infrastructure—a reversible change that affects resource configurations.
Attacks that exploit this kind of access
Apply a firewall to servers or a label selector. Pass apply_to: [{ type:. It is categorised as a Write tool in the Hcloud MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Hcloud MCP server in PolicyLayer and add a rule for apply_firewall_to_resources: 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.
apply_firewall_to_resources 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 apply_firewall_to_resources 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 apply_firewall_to_resources. 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.
apply_firewall_to_resources 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 →