AI agents call analyze_db_health to retrieve information from Postgres without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Health check tools query database metadata and status metrics without creating, modifying, or deleting data. No side effects are triggered by running diagnostics. This is clearly a Read operation with low blast radius—misuse would only surface monitoring data or cause minor performance overhead, not compromise data integrity.
From the tool's definition Tool name 'analyze_db_health' and description 'Analyzes database health' indicate a diagnostic, read-only operation. The description explicitly lists 'health checks' as the function, which are typically non-mutating queries that examine system state.
Attacks that exploit this kind of access
Analyzes database health. Here are the available health checks:\n. It is categorised as a Read tool in the Postgres MCP Server, which means it retrieves data without modifying state.
Register the Postgres MCP server in PolicyLayer and add a rule for analyze_db_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 Postgres. Nothing to install.
analyze_db_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 analyze_db_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 analyze_db_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.
analyze_db_health is provided by the Postgres MCP server (mirenqinggege/postgres-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 →