AI agents call get_usage_stats to retrieve information from OpenRouter MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to fetch usage statistics, a read-only operation with no side effects. Even if misused by an AI agent, retrieving usage data poses minimal security risk—it exposes only existing metrics without modifying system state or triggering external actions. Low confidence due to empty description, but the naming convention strongly suggests a monitoring/analytics retrieval function.
From the tool's definition Tool name 'get_usage_stats' indicates retrieval of usage statistics. The description is empty, but naming patterns in the server (list_available_models, list_free_models, get_free_model_metrics) suggest this is a data retrieval function.
Documented attack patterns abuse exactly the kind of access get_usage_stats gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenRouter MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_usage_stats:
{
"version": "1",
"default": "deny",
"tools": {
"get_usage_stats": {}
}
}get_usage_stats 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_usage_stats. It is categorised as a Read tool in the OpenRouter MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenRouter MCP Server MCP server in PolicyLayer and add a rule for get_usage_stats: 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 OpenRouter MCP Server. Nothing to install.
get_usage_stats 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_usage_stats 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_usage_stats. 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_usage_stats is provided by the OpenRouter MCP Server MCP server (physics91/openrouter-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OpenRouter 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.
9 OpenRouter MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.