Query audit log entries (auth events, config changes).
AI agents call get_audit_log to retrieve information from Truenas Ws without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Querying audit logs is a read-only operation that retrieves existing log data without side effects. No data is created, modified, deleted, or executed. The blast radius is minimal—an AI agent could at worst retrieve sensitive audit information, but cannot alter system state or logs themselves through this tool.
From the tool's definition Tool name is 'get_audit_log' and description states 'Query audit log entries' — verb 'query' and 'get' indicate retrieval only. Audit logs are read-only historical records of events (auth events, config changes) with no modification or deletion capability.
Attacks that exploit this kind of access
Query audit log entries (auth events, config changes). It is categorised as a Read tool in the Truenas Ws MCP Server, which means it retrieves data without modifying state.
Register the Truenas Ws MCP server in PolicyLayer and add a rule for get_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 Truenas Ws. Nothing to install.
get_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 get_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 get_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.
get_audit_log is provided by the Truenas Ws MCP server (thoriphes/truenas-ws-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 →