Execute insert/update/delete/truncate to the oracle database
AI agents call exec_dml_sql to permanently remove resources in Oracle MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool executes DML operations including DELETE and TRUNCATE, which can irreversibly destroy or modify data at scale. TRUNCATE in particular removes all rows from a table instantly and cannot be rolled back in most configurations. Even UPDATE and DELETE can cause massive irreversible data loss if misused by an AI agent.
From the tool's definition Execute insert/update/delete/truncate to the oracle database
Attacks that exploit this kind of access
Execute insert/update/delete/truncate to the oracle database. It is categorised as a Destructive tool in the Oracle MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Oracle MCP Server MCP server in PolicyLayer and add a rule for exec_dml_sql: 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 MCP Server. Nothing to install.
exec_dml_sql 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 exec_dml_sql 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 exec_dml_sql. 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.
exec_dml_sql is provided by the Oracle MCP Server MCP server (zhengwanbo/oracle-mcp-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 →