AI agents use remove_firewall_from_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.
Removing a firewall from servers is a reversible write operation (the firewall can be re-applied), but it carries high severity because it exposes servers to network traffic that was previously blocked, potentially opening security vulnerabilities. It modifies security posture but does not irreversibly delete any data or resource.
From the tool's definition remove_firewall_from_resources — removes a firewall from servers, reversing a security configuration
Attacks that exploit this kind of access
Remove a firewall from servers. Pass remove_from: [{ 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 remove_firewall_from_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.
remove_firewall_from_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 remove_firewall_from_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 remove_firewall_from_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.
remove_firewall_from_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 →