AI agents call irr_autnum 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.
IRR (Internet Routing Registry) autnum queries are standard network diagnostic operations that read and return existing routing registry entries. No side effects, no data modification, no code execution. Consistent with sibling tools (bgp_asn_info, bgp_prefix_origin, dns_lookup) which are all Read-category information retrieval.
From the tool's definition Tool name 'irr_autnum' suggests querying Internet Routing Registry (IRR) data for autonomous system information. No description provided, but IRR lookups are informational/analytical queries that retrieve public registry data without modifying state.
Attacks that exploit this kind of access
irr_autnum. 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 irr_autnum: 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.
irr_autnum 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 irr_autnum 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 irr_autnum. 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.
irr_autnum 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 →