Get current usage and quota for your API key.
AI agents call get_usage to retrieve information from QR for Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays usage statistics and quota information—a pure read operation with no side effects, no state changes, and no capability to execute code or commands. The blast radius of misuse is minimal (information disclosure only). It fits squarely in the Read category.
From the tool's definition Tool name 'get_usage' and description 'Get current usage and quota for your API key' indicate a retrieval operation that queries API metrics without modifying or executing actions.
Attacks that exploit this kind of access
Get current usage and quota for your API key. It is categorised as a Read tool in the QR for Agent MCP Server, which means it retrieves data without modifying state.
Register the QR for Agent MCP server in PolicyLayer and add a rule for get_usage: 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 QR for Agent. Nothing to install.
get_usage 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 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. 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 is provided by the QR for Agent MCP server (qr-for-agent). 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 →