Query the audit log of tool calls.
AI agents call audit_log 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 audit log data for inspection and compliance purposes. While the audit log itself may be sensitive (containing information about who called what and when), the tool performs only a read operation and does not modify, delete, or execute anything. It is a query-based tool consistent with the Read category.
From the tool's definition Tool name is 'audit_log' and description states 'Query the audit log of tool calls.' The verb 'query' combined with 'audit log' indicates a read-only retrieval operation with no side effects.
Attacks that exploit this kind of access
Query the audit log of tool calls. 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_log: 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_log 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_log 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_log. 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_log 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 →