AI agents call get_user_policy 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 'get_' prefix strongly suggests this tool retrieves policy information associated with a user without modifying state. This aligns with Read category semantics. However, the empty description reduces confidence to 0.7. The tool appears to query AWS IAM user policy details, which is a non-destructive read operation with low blast radius if misused—an agent could only view policy information, not alter it.
From the tool's definition Tool name 'get_user_policy' indicates a retrieval operation following common naming conventions for read operations (get_* pattern). Description is empty, limiting certainty.
Documented attack patterns abuse exactly the kind of access get_user_policy 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 get_user_policy:
{
"version": "1",
"default": "deny",
"tools": {
"get_user_policy": {}
}
}get_user_policy 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.
get_user_policy. 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 get_user_policy: 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.
get_user_policy 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 get_user_policy 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 get_user_policy. 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.
get_user_policy 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.