audit_instance_health
AI agents call audit_instance_health to retrieve information from Looker MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Health auditing is fundamentally a diagnostic read operation that queries instance status without creating, modifying, deleting, or executing changes to data or infrastructure. While the empty description reduces certainty, the name and context of Looker administration strongly indicate a monitoring/read capability. Confidence is moderate due to missing documentation.
From the tool's definition Tool name 'audit_instance_health' suggests checking system status and health metrics; the server description indicates this is a Looker admin tool for monitoring.
Attacks that exploit this kind of access
audit_instance_health. It is categorised as a Read tool in the Looker MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Looker MCP Server MCP server in PolicyLayer and add a rule for audit_instance_health: 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 Looker MCP Server. Nothing to install.
audit_instance_health 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_instance_health 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_instance_health. 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_instance_health is provided by the Looker MCP Server MCP server (ultrathink-solutions/looker-mcp-server). 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 →