AI agents use change_server_type to create or update resources in Hcloud — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Hcloud environment.
This tool modifies the server configuration by changing its type/size, which is a reversible write operation (you can change it back). However, it has high severity because misuse could scale a server to a much larger (and more expensive) type, significantly increasing infrastructure costs. It's not purely Financial as it doesn't directly move money, but the cost implications are substantial.
From the tool's definition 'Change the type of a server (scales resources). Server must be powered off.'
Attacks that exploit this kind of access
Change the type of a server (scales resources). Server must be powered off. It is categorised as a Write tool in the Hcloud MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Hcloud MCP server in PolicyLayer and add a rule for change_server_type: 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.
change_server_type is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the change_server_type 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 change_server_type. 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.
change_server_type 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 →