AI agents call PostgreSQL_drop_user 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.
This tool performs an irreversible destructive action by removing a database user/role. Even if the user had no active sessions or permissions, dropping it permanently eliminates the role definition from the database and severs any associated privileges.
From the tool's definition Tool name contains 'drop_user' and description states 'Drop a database user/role' — drop is an irreversible deletion operation in SQL/PostgreSQL that removes the user/role and cannot be undone without restoration from backup.
Documented attack patterns abuse exactly the kind of access PostgreSQL_drop_user gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Postgres, and nothing reaches the server without passing your rules. This is the rule we recommend for PostgreSQL_drop_user:
{
"version": "1",
"default": "deny",
"hide": [
"PostgreSQL_drop_user"
]
}PostgreSQL_drop_user disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Drop a database user/role. 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 PostgreSQL_drop_user: 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.
PostgreSQL_drop_user 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 PostgreSQL_drop_user 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 PostgreSQL_drop_user. 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.
PostgreSQL_drop_user is provided by the Postgres MCP server (mukul975/postgres-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Postgres, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
239 Postgres tools catalogued and risk-classified — across an index of 43,000+ MCP servers.