AI agents use unassign_floating_ip 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.
Unassigning a floating IP is a reversible modification of cloud infrastructure state. The floating IP itself is not deleted, but its assignment is changed. This is a Write operation—it alters configuration reversibly. While it could cause service disruption if misapplied (affecting network accessibility), it is not destructive (the IP and resources remain), not financial, and not arbitrary code execution.
From the tool's definition Tool name is 'unassign_floating_ip' and description states 'Unassign a floating IP'. This operation modifies network configuration by removing the association between a floating IP and a resource.
Attacks that exploit this kind of access
Unassign a floating IP. 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 unassign_floating_ip: 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.
unassign_floating_ip 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 unassign_floating_ip 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 unassign_floating_ip. 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.
unassign_floating_ip 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 →