Delete a server
AI agents call delete_server 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 server permanently removes the compute instance and associated resources from the cloud infrastructure. This action is irreversible and represents the highest-risk category. An AI agent misusing this tool could destroy production infrastructure, cause data loss, and incur significant operational impact. The blast radius is critical given the foundational nature of servers in cloud deployments.
From the tool's definition Tool name 'delete_server' combined with description 'Delete a server' explicitly indicates irreversible deletion of cloud infrastructure. This is a destructive operation that cannot be undone.
Attacks that exploit this kind of access
Delete a server. 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_server: 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_server 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_server 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_server. 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_server 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 →