Drop a function from the PostgreSQL database by its name.
AI agents call drop_function to permanently remove resources in Pgmcp — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The DROP operation in PostgreSQL is irreversible and cannot be undone without a backup. Misuse by an AI agent could permanently remove critical database functions, breaking application logic and causing data integrity issues. This is more severe than Write (reversible modifications) but not Financial. High severity reflects the potential for significant operational impact, though not system-wide catastrophic failure.
From the tool's definition Tool name 'drop_function' and description 'Drop a function from the PostgreSQL database' explicitly indicate irreversible deletion of database objects.
Attacks that exploit this kind of access
Drop a function from the PostgreSQL database by its name. It is categorised as a Destructive tool in the Pgmcp MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pg MCP server in PolicyLayer and add a rule for drop_function: 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 Pgmcp. Nothing to install.
drop_function 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 drop_function 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 drop_function. 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.
drop_function is provided by the Pg MCP server (veloper/pgmcp). 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 →