Power on a server that is currently off.
AI agents invoke hetzner_power_on_server to trigger actions in Hetzner MCP Server. 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 operation (starting a cloud VM) that has real-world side effects such as incurring compute costs and launching running processes. It does not read, write, or delete data, nor is it directly financial or destructive — it falls squarely in Execute. Misuse could cause unintended servers to start running and accumulate charges, hence medium severity.
From the tool's definition Power on a server that is currently off
Attacks that exploit this kind of access
Power on a server that is currently off. It is categorised as a Execute tool in the Hetzner MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Hetzner MCP Server MCP server in PolicyLayer and add a rule for hetzner_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 Hetzner MCP Server. Nothing to install.
hetzner_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 hetzner_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 hetzner_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.
hetzner_power_on_server is provided by the Hetzner MCP Server MCP server (jurislm/hetzner-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 →