Get usage metrics (calls, latency, errors) by consumer or server.
AI agents call usage to retrieve information from MCP Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical metrics and statistics for consumption reporting and monitoring. It has no capability to modify infrastructure, execute operations, or affect system state. The data returned is observational telemetry suitable for read-only access. Within an MCP Gateway context, usage metrics are typically aggregated and non-sensitive operational data.
From the tool's definition Tool returns usage metrics (calls, latency, errors) for monitoring purposes. Described as 'get' operation with no modification or side effects.
Attacks that exploit this kind of access
Get usage metrics (calls, latency, errors) by consumer or server. It is categorised as a Read tool in the MCP Gateway MCP Server, which means it retrieves data without modifying state.
Register the MCP Gateway MCP server in PolicyLayer and add a rule for 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 MCP Gateway. Nothing to install.
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 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 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.
usage is provided by the MCP Gateway MCP server (petrefiedthunder/mcp-gateway). 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 →