Delete rows from a table
AI agents call delete_data to permanently remove resources in PostgreSQL MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of data cannot be undone without a prior backup. Even with row-level specificity, this operation permanently removes data from the database. In a multi-tenant or production environment, misuse by an AI agent (e.g., deleting the wrong table/rows due to prompt injection or logical error) could cause severe data loss.
From the tool's definition Tool name is 'delete_data' and description states 'Delete rows from a table' — this is an irreversible deletion operation.
Attacks that exploit this kind of access
Delete rows from a table. It is categorised as a Destructive tool in the PostgreSQL MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the PostgreSQL MCP Server MCP server in PolicyLayer and add a rule for delete_data: 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 MCP Server. Nothing to install.
delete_data 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_data 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_data. 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_data is provided by the PostgreSQL MCP Server MCP server (reckersai/mcpg). 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 →