Remove a table from the database with safety confirmation
AI agents call drop_table to permanently remove resources in MCP Database Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
drop_table performs an irreversible deletion operation that cannot be undone without database backups. Although it includes a 'safety confirmation', confirmation is a UI/UX control that does not change the destructive nature of the action itself. An AI agent with access to this tool could be tricked into dropping critical tables, causing permanent data loss.
From the tool's definition Tool name is 'drop_table' and description states 'Remove a table from the database' — dropping a table irreversibly deletes all data and schema within it.
Attacks that exploit this kind of access
Remove a table from the database with safety confirmation. It is categorised as a Destructive tool in the MCP Database Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Database Server MCP server in PolicyLayer and add a rule for drop_table: 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 MCP Database Server. Nothing to install.
drop_table 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_table 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_table. 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_table is provided by the MCP Database Server MCP server (shailesh5050/mcp-database-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 →