AI agents use update_ssh_key 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 creates or modifies data in a reversible manner (updating name and labels of an SSH key). It does not execute code, delete data irreversibly, or move money. The severity is medium because SSH keys are security-sensitive assets; misuse could modify key metadata in ways that obscure audit trails or cause operational confusion, but the changes themselves are not destructive and can be reverted.
From the tool's definition Tool is described as 'Update an SSH key (name, labels)' — explicitly modifies existing data (name and labels fields) reversibly without deletion or destruction.
Attacks that exploit this kind of access
Update an SSH key (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_ssh_key: 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_ssh_key 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_ssh_key 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_ssh_key. 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_ssh_key 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 →