AI agents call bgp_leaks 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.
BGP leak detection retrieves and analyzes network routing data; it has no capacity to modify, delete, or execute code. The blast radius is medium because misuse could map network vulnerabilities, but the tool itself only reads public BGP data. Confidence is moderate (0.7) due to empty description—if this tool actually triggers network scans or has side effects, classification would shift to Execute or higher.
From the tool's definition Tool name 'bgp_leaks' combined with sibling tools focused on BGP analysis (bgp_asn_info, bgp_hijacks, bgp_historical_lookup, bgp_prefix_origin, bgp_route_lookup) and RPKI validation.
Attacks that exploit this kind of access
bgp_leaks. 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 bgp_leaks: 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.
bgp_leaks 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 bgp_leaks 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 bgp_leaks. 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.
bgp_leaks 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 →