AI agents call supernet_aggregate to retrieve information from Net without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or processes IP prefix data to compute aggregate supernets. It has no side effects on network infrastructure, data stores, or external systems. It is a read-only analytical operation that transforms input data into structured output without persisting changes or executing commands.
From the tool's definition The tool 'supernet_aggregate' performs aggregation of IP prefixes into a supernet—a computational operation that analyzes and transforms IP address data without modifying any external systems, databases, or network configurations.
Attacks that exploit this kind of access
Try to aggregate a list of IP prefixes into a supernet. It is categorised as a Read tool in the Net MCP Server, which means it retrieves data without modifying state.
Register the Net MCP server in PolicyLayer and add a rule for supernet_aggregate: 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 Net. Nothing to install.
supernet_aggregate is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the supernet_aggregate 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 supernet_aggregate. 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.
supernet_aggregate is provided by the Net MCP server (steelcutoatmeal/net-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 →