AI agents invoke reset_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 hard reset is an abrupt power-cycle of a running server. It is not a graceful reboot and can cause data corruption or service disruption, but it does not irreversibly delete data. It falls under Execute (triggers external infrastructure operation) rather than Destructive, since the server and its data remain intact after the reset.
From the tool's definition 'Reset a server (hard)' — a hard reset forcibly restarts a server without graceful shutdown, triggering an external operation on cloud infrastructure
Attacks that exploit this kind of access
Reset a server (hard). 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 reset_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.
reset_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 reset_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 reset_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.
reset_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.
reset_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 →