Lists NAT Gateways with their state and public IP.
AI agents call list_nat_gateways to retrieve information from AWS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries NAT Gateway configuration and status information. It has no side effects, cannot modify resources, and presents no destructive or financial risk. The blast radius of misuse is minimal — an agent could at worst enumerate NAT Gateway resources in the AWS environment, which is low-impact reconnaissance.
From the tool's definition Tool is described as 'Lists NAT Gateways with their state and public IP' — a pure query operation returning infrastructure metadata with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Lists NAT Gateways with their state and public IP. It is categorised as a Read tool in the AWS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AWS MCP Server MCP server in PolicyLayer and add a rule for list_nat_gateways: 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 AWS MCP Server. Nothing to install.
list_nat_gateways 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 list_nat_gateways 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 list_nat_gateways. 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.
list_nat_gateways is provided by the AWS MCP Server MCP server (sergiosediq/aws-mcp-server). 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 →