AI agents invoke shutdown_server to trigger actions in Hcloud. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
A soft shutdown sends a shutdown signal to the server's OS, halting all running workloads. This is an external operation with significant operational impact (service disruption) but is generally reversible (server can be restarted), placing it in Execute rather than Destructive. Misuse by an AI agent could cause outages for production services.
From the tool's definition 'Shutdown a server (soft)' — triggers an OS-level shutdown operation on a cloud server
Attacks that exploit this kind of access
Shutdown a server (soft). It is categorised as a Execute tool in the Hcloud MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Hcloud MCP server in PolicyLayer and add a rule for shutdown_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.
shutdown_server is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the shutdown_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 shutdown_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.
shutdown_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.
shutdown_server is one line of Hcloud's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →