Lists AWS security groups with their details including inbound and outbound rules.
AI agents call list_security_groups to retrieve information from AWS Security 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 security group metadata and rules without creating, modifying, deleting, or executing operations. It has no side effects and poses minimal risk if invoked—it only exposes existing security posture information that an authorized user would typically be permitted to view.
From the tool's definition Tool name contains 'list' and description states 'Lists AWS security groups with their details'; performs retrieval of existing security group configuration data with no modification capability.
Documented attack patterns abuse exactly the kind of access list_security_groups gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AWS Security MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for list_security_groups:
{
"version": "1",
"default": "deny",
"tools": {
"list_security_groups": {}
}
}list_security_groups is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Lists AWS security groups with their details including inbound and outbound rules. It is categorised as a Read tool in the AWS Security MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AWS Security MCP Server MCP server in PolicyLayer and add a rule for list_security_groups: 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 Security MCP Server. Nothing to install.
list_security_groups 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_security_groups 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_security_groups. 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_security_groups is provided by the AWS Security MCP Server MCP server (skjortan23/aws-security-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AWS Security MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 AWS Security MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.