Get audit log statistics (total calls, by status, by server).
AI agents call audit_stats 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 aggregate statistics from audit logs—a summarized view of call counts grouped by status and server. It has no ability to modify, delete, or trigger any actions. The blast radius of misuse is minimal: an attacker gaining access could only learn about call patterns and system usage, not alter systems or data. Classified as Read/low severity.
From the tool's definition Tool name 'audit_stats' combined with description 'Get audit log statistics' indicates a query/retrieval operation.
Attacks that exploit this kind of access
Get audit log statistics (total calls, by status, by 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 audit_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 MCP Gateway. Nothing to install.
audit_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 audit_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 audit_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.
audit_stats 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 →