Get a summary of audit activity
AI agents call security_audit_summary to retrieve information from ML Lab MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and summarizes audit activity logs without creating, modifying, deleting, or executing anything. It is a read-only operation that queries historical audit data. The low severity reflects minimal blast radius—even if misused, an AI agent can only view audit summaries, not alter systems or data.
From the tool's definition Tool name 'security_audit_summary' and description 'Get a summary of audit activity' indicate a retrieval/query operation. The verb 'Get' and the focus on retrieving a summary of existing audit data with no modification capability.
Attacks that exploit this kind of access
Get a summary of audit activity. It is categorised as a Read tool in the ML Lab MCP MCP Server, which means it retrieves data without modifying state.
Register the ML Lab MCP server in PolicyLayer and add a rule for security_audit_summary: 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 ML Lab MCP. Nothing to install.
security_audit_summary 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 security_audit_summary 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 security_audit_summary. 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.
security_audit_summary is provided by the ML Lab MCP server (pushpullcommitpush/ml-mcp). 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 →