AI agents call db_postgres_health to retrieve information from Infra Ops without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs health monitoring and status checks of PostgreSQL databases. It retrieves metadata (version, connection count, database size) which are read-only operations with no side effects. No data is modified, deleted, or code is executed. This fits the 'Read' category as a diagnostic/query tool for observability purposes.
From the tool's definition Tool description states 'Check PostgreSQL database health' with read-only operations: 'version, connections, and size'. These are all diagnostic queries that retrieve information without modifying or executing code.
Attacks that exploit this kind of access
Check PostgreSQL database health including version, connections, and size. It is categorised as a Read tool in the Infra Ops MCP Server, which means it retrieves data without modifying state.
Register the Infra Ops MCP server in PolicyLayer and add a rule for db_postgres_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 Infra Ops. Nothing to install.
db_postgres_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 db_postgres_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 db_postgres_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.
db_postgres_health is provided by the Infra Ops MCP server (skyvanguard/infra-ops-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 →