AI agents use add_network_subnet 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 a new subnet, which is a Write operation (reversible data modification). The severity is medium because misconfiguration of subnets could affect network connectivity and isolation across cloud infrastructure, but the impact is contained to network topology and does not directly delete resources (Destructive) or execute arbitrary code (Execute).
From the tool's definition "Add a subnet to a network" – creates a new subnet resource within an existing network, modifying network configuration. This is a reversible creation operation that adds infrastructure elements.
Attacks that exploit this kind of access
Add a subnet to a network (e.g. for private networking 10.0.0.0/16 in a zone). 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 add_network_subnet: 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.
add_network_subnet 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 add_network_subnet 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 add_network_subnet. 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.
add_network_subnet 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 →