AI agents call get_usage to retrieve information from RendrKit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries usage metrics and plan information, which is a read-only operation with no side effects. The blast radius of misuse is minimal—an attacker could only view usage data, not modify services, generate images without authorization, or access sensitive billing details beyond their own quota information.
From the tool's definition Tool name and description indicate data retrieval only: 'Check current usage statistics including images generated this month and plan limits'. No modification, deletion, execution, or financial operations are performed.
Attacks that exploit this kind of access
Check current usage statistics including images generated this month and plan limits. It is categorised as a Read tool in the RendrKit MCP Server, which means it retrieves data without modifying state.
Register the RendrKit 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 RendrKit. 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 RendrKit MCP server (vbiff/rendrkit-mcp-server). 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 →