AI agents call describe_services to retrieve information from Prometheus MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'describe_*' naming pattern in AWS APIs universally indicates read-only operations that retrieve and return information about resources. Given the Prometheus server context, this tool likely queries service configurations or metrics metadata. Without evidence of mutation, execution, deletion, or financial operations, and based on standard AWS API conventions, this is classified as Read with low severity.
From the tool's definition Tool name 'describe_services' indicates a query operation that retrieves service metadata without modifying state. No description provided, but naming convention and context within AWS Prometheus MCP server suggests read-only introspection.
Documented attack patterns abuse exactly the kind of access describe_services gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Prometheus MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for describe_services:
{
"version": "1",
"default": "deny",
"tools": {
"describe_services": {}
}
}describe_services 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_services. It is categorised as a Read tool in the Prometheus MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Prometheus MCP Server MCP server in PolicyLayer and add a rule for describe_services: 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 Prometheus MCP Server. Nothing to install.
describe_services 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_services 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_services. 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_services is provided by the Prometheus MCP Server MCP server (awslabs.prometheus-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Prometheus 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.
805 Prometheus MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.