AI agents call get_table_stats 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.
get_table_stats queries and returns table metadata and performance statistics without altering data or triggering side effects. This is a typical monitoring/observability operation that falls squarely into the Read category. The low severity reflects that misuse cannot corrupt, delete, or expose sensitive table contents—only aggregate statistics visible to any database user with schema visibility.
From the tool's definition Tool description states it retrieves 'statistics for a table: row count, sizes, sequential vs index scans, dead tuples' — purely informational metrics about table characteristics with no modification or deletion capability.
Attacks that exploit this kind of access
Get statistics for a table: row count, sizes, sequential vs index scans, dead tuples. 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 get_table_stats: 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.
get_table_stats 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_table_stats 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_table_stats. 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_table_stats is provided by the Postgres MCP server (madhurprash/postgres-mcp-agentcore). 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 →