Execute PL/SQL code blocks including stored procedures, functions and anonymous blocks
AI agents invoke exec_pro_sql to trigger actions in Oracle MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes PL/SQL code, which can perform arbitrary database operations depending on what code is passed to it. While the sibling tools exec_ddl_sql and exec_dml_sql suggest this server permits data definition and manipulation, exec_pro_sql specifically targets procedural code execution (stored procedures, functions, anonymous blocks).
From the tool's definition Tool description states 'Execute PL/SQL code blocks including stored procedures, functions and anonymous blocks'.
Attacks that exploit this kind of access
Execute PL/SQL code blocks including stored procedures, functions and anonymous blocks. It is categorised as a Execute tool in the Oracle MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Oracle MCP Server MCP server in PolicyLayer and add a rule for exec_pro_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_pro_sql is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the exec_pro_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_pro_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_pro_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 →