AI agents invoke power_on_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.
Powering on a server triggers an external infrastructure operation. It is not a simple data read or write, but an execution of a state change on a live cloud resource. It is reversible (the server can be powered off), so it is not Destructive, but it does execute an action with real-world side effects such as incurring compute costs and starting services.
From the tool's definition 'Power on a server' — triggers an external operation that starts a cloud server instance
Attacks that exploit this kind of access
Power on a server. 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 power_on_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.
power_on_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 power_on_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 power_on_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.
power_on_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 →