AI agents use create_firewall 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.
This tool creates a new firewall resource in Hetzner Cloud infrastructure. While creation is reversible (the firewall can be deleted), it establishes security policies that could block or allow network traffic. The impact is significant but not irreversible or destructive.
From the tool's definition Tool name 'create_firewall' and description 'Create a new firewall' indicate data creation. The 'Rules: direction' parameter suggests configuration of firewall rules that can be modified.
Attacks that exploit this kind of access
Create a new firewall. Rules: direction. 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 create_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.
create_firewall 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 create_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 create_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.
create_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 →