AI agents call mrt_search 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.
MRT files contain archived BGP routing table dumps used for network analysis. A search operation on such data is a read-only query with no side effects. Empty description lowers confidence slightly, but the tool's position among similar read-only network diagnostic tools and the 'search' verb strongly suggest retrieval without modification or execution.
From the tool's definition Tool name 'mrt_search' suggests searching through MRT (Multi-threaded Routing Toolkit) data; sibling tools like 'bgp_asn_info', 'bgp_historical_lookup', and 'bgp_route_lookup' are all read-only BGP queries.
Attacks that exploit this kind of access
mrt_search. 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 mrt_search: 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.
mrt_search 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 mrt_search 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 mrt_search. 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.
mrt_search 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 →