AI agents use update_load_balancer 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 load balancer attributes (name and labels) but does not create, delete, or execute arbitrary operations. Changes to name and labels are reversible and do not constitute destructive operations. The severity is medium because misconfiguration could impact traffic routing or infrastructure management, but the blast radius is limited to metadata updates on a single load balancer resource.
From the tool's definition Tool name is 'update_load_balancer' and description states it updates load balancer 'name, labels' — these are reversible modifications to existing infrastructure configuration.
Attacks that exploit this kind of access
Update a load balancer (name, labels). 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 update_load_balancer: 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.
update_load_balancer 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 update_load_balancer 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 update_load_balancer. 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.
update_load_balancer 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 →