remove_load_balancer_target · Hcloud MCP: Risk & Policy

WHAT IT DOES

What remove_load_balancer_target does on Hcloud

AI agents use remove_load_balancer_target 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.

WHY IT NEEDS A POLICY

Why remove_load_balancer_target needs a policy

Removing a load balancer target detaches a server/resource from the load balancer, stopping traffic routing to it. This is a reversible configuration change (the target can be re-added), placing it in the Write category. However, misuse could cause service disruption by inadvertently removing healthy targets from production load balancers, warranting medium severity.

From the tool's definition 'Remove a target from a load balancer' — removes a target association but does not destroy the underlying resource itself

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

remove_load_balancer_target Rate-limited

remove_load_balancer_target stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "remove_load_balancer_target": {
      "limits": [
        {
          "counter": "remove_load_balancer_target_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Hcloud, so you can run agents against it safely.

FAQ

Questions about remove_load_balancer_target

What does the remove_load_balancer_target tool do? +

Remove a target from a load balancer. 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.

How do I enforce a policy on remove_load_balancer_target? +

Register the Hcloud MCP server in PolicyLayer and add a rule for remove_load_balancer_target: 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.

What risk level is remove_load_balancer_target? +

remove_load_balancer_target is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit remove_load_balancer_target? +

Yes. Add a rate_limit block to the remove_load_balancer_target 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.

How do I block remove_load_balancer_target completely? +

Set action: deny in the PolicyLayer policy for remove_load_balancer_target. 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.

What MCP server provides remove_load_balancer_target? +

remove_load_balancer_target 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.