DELETE rows matching a WHERE clause and return the deleted records
AI agents call delete_rows to permanently remove resources in Postgres — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
DELETE operations are irreversible and permanently remove data. Even though the tool returns the deleted records (providing some auditability), the core action cannot be undone without manual intervention or backups. This qualifies as Destructive rather than Execute because deletion is the primary purpose and effect, not merely a side effect of code execution.
From the tool's definition Tool description explicitly states 'DELETE rows matching a WHERE clause' — a destructive operation that irreversibly removes data from the database. The tool allows deletion of potentially multiple rows based on a WHERE clause condition.
Attacks that exploit this kind of access
DELETE rows matching a WHERE clause and return the deleted records. It is categorised as a Destructive tool in the Postgres MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Postgres MCP server in PolicyLayer and add a rule for delete_rows: 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.
delete_rows is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_rows 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 delete_rows. 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.
delete_rows is provided by the Postgres MCP server (santisanti13/postgres-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 →