Execute a DDL or DML statement (CREATE, INSERT, UPDATE, DELETE, ALTER, DROP).
AI agents call execute_ddl to permanently remove resources in Oracle Sqlplus — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool explicitly supports DROP (irreversible deletion of database objects) and DELETE (irreversible data removal), as well as ALTER and other DDL/DML operations. Since DROP and DELETE are destructive and irreversible, and following the most-severe-category rule, this tool is classified as Destructive with critical severity given the blast radius of dropping tables or schemas in a production Oracle database.
From the tool's definition Execute a DDL or DML statement (CREATE, INSERT, UPDATE, DELETE, ALTER, DROP)
Attacks that exploit this kind of access
Execute a DDL or DML statement (CREATE, INSERT, UPDATE, DELETE, ALTER, DROP). It is categorised as a Destructive tool in the Oracle Sqlplus MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Oracle Sqlplus MCP server in PolicyLayer and add a rule for execute_ddl: 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 Oracle Sqlplus. Nothing to install.
execute_ddl 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 execute_ddl 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 execute_ddl. 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.
execute_ddl is provided by the Oracle Sqlplus MCP server (sagar1012/oracle-sqlplus-mcp). 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 →