AI agents use update_placement_group 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 existing cloud infrastructure metadata reversibly. Updating a placement group's name and labels are non-destructive write operations that can be reverted. While placement groups affect server organization and networking behavior, the action itself is a configuration update rather than creation, deletion, or code execution.
From the tool's definition Tool description states 'Update a placement group (name, labels)' - updates existing configuration data (name and labels) on a placement group resource without deleting or destroying it.
Attacks that exploit this kind of access
Update a placement group (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_placement_group: 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_placement_group 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_placement_group 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_placement_group. 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_placement_group 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 →