Drop/delete a database
AI agents call drop_database to permanently remove resources in MCP Server MySQL — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Dropping a database is an irreversible destructive action that cannot be undone without a backup. The blast radius is maximal: loss of all data in that database. This is categorized as Destructive (the most severe category applicable) rather than Execute because the action itself is inherently destructive by design, not merely a code execution whose effects depend on benign arguments.
From the tool's definition Tool name is 'drop_database' and description states 'Drop/delete a database' — this irreversibly removes an entire database and all its contents.
Attacks that exploit this kind of access
Drop/delete a database. It is categorised as a Destructive tool in the MCP Server MySQL MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Server MySQL MCP server in PolicyLayer and add a rule for drop_database: 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 Server MySQL. Nothing to install.
drop_database 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_database 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_database. 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_database is provided by the MCP Server MySQL MCP server (nilsir/mcp-server-mysql). 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 →