Get API usage statistics
AI agents call getUsage to retrieve information from Random Org MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns usage data with no side effects. It is a read-only operation that retrieves information about the API account's usage metrics. There is no capacity to modify data, execute code, delete resources, or affect financial state. The blast radius of misuse is minimal—an attacker could only learn usage patterns and quota consumption, which poses low risk.
From the tool's definition The tool name is "getUsage" and description states "Get API usage statistics" - this retrieves statistics about API consumption without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
Get API usage statistics. It is categorised as a Read tool in the Random Org MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Random Org MCP Server MCP server in PolicyLayer and add a rule for getUsage: 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 Random Org MCP Server. Nothing to install.
getUsage 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 getUsage 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 getUsage. 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.
getUsage is provided by the Random Org MCP Server MCP server (qianjue-cn/truerandommcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →