Check vacuum health across a schema. Reports tables with high dead row ratios that need vacuuming, along with last vacuum/autovacuum timestamps. Dead rows accumulate from UPDATE/DELETE operations and waste disk space.
AI agents call vacuumHealth to retrieve information from Postgresql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and reports diagnostic information about vacuum health status (dead row ratios, timestamps). It does not modify, delete, or execute anything — it is purely observational/diagnostic.
From the tool's definition 'Check vacuum health across a schema. Reports tables with high dead row ratios... along with last vacuum/autovacuum timestamps.'
Attacks that exploit this kind of access
Check vacuum health across a schema. Reports tables with high dead row ratios that need vacuuming, along with last vacuum/autovacuum timestamps. Dead rows accumulate from UPDATE/DELETE operations and waste disk space. It is categorised as a Read tool in the Postgresql MCP Server, which means it retrieves data without modifying state.
Register the Postgresql MCP server in PolicyLayer and add a rule for vacuumHealth: 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 Postgresql. Nothing to install.
vacuumHealth 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 vacuumHealth 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 vacuumHealth. 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.
vacuumHealth is provided by the Postgresql MCP server (vnikhilbuddhavarapu/postgresql-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 →