AI agents call describe_severity_levels to retrieve information from Awslabs Amazon Sns Sqs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The verb 'describe' clearly suggests a read-only operation that retrieves information about severity levels (likely configuration or metadata). No evidence of side effects, data modification, or external operations. This is consistent with Read category tools that query or fetch information.
From the tool's definition Tool name 'describe_severity_levels' uses the verb 'describe', which indicates retrieval or querying of data without modification. The description is empty, limiting confidence.
Documented attack patterns abuse exactly the kind of access describe_severity_levels gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Awslabs Amazon Sns Sqs, and nothing reaches the server without passing your rules. This is the rule we recommend for describe_severity_levels:
{
"version": "1",
"default": "deny",
"tools": {
"describe_severity_levels": {}
}
}describe_severity_levels 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.
describe_severity_levels. It is categorised as a Read tool in the Awslabs Amazon Sns Sqs MCP Server, which means it retrieves data without modifying state.
Register the Awslabs Amazon Sns Sqs MCP server in PolicyLayer and add a rule for describe_severity_levels: 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 Awslabs Amazon Sns Sqs. Nothing to install.
describe_severity_levels 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 describe_severity_levels 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 describe_severity_levels. 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.
describe_severity_levels is provided by the Awslabs Amazon Sns Sqs MCP server (awslabs.amazon-sns-sqs-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Awslabs Amazon Sns Sqs, 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.
805 Awslabs Amazon Sns Sqs tools catalogued and risk-classified — across an index of 43,000+ MCP servers.