Return Oracle EXPLAIN PLAN output for a SELECT query.
AI agents call explain_plan to retrieve information from Mcp Oracle Dba without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
EXPLAIN PLAN analyzes a SQL statement and returns the optimizer's execution plan. It does not execute the query, modify data, or have any side effects. The server is also described as read-only with SQL guards, further confirming this is a safe read operation. Severity is low because misuse is limited to information disclosure about query structure.
From the tool's definition 'Return Oracle EXPLAIN PLAN output for a SELECT query' — this only generates and retrieves the execution plan for a query without executing it or modifying any data.
Attacks that exploit this kind of access
Return Oracle EXPLAIN PLAN output for a SELECT query. It is categorised as a Read tool in the Mcp Oracle Dba MCP Server, which means it retrieves data without modifying state.
Register the Mcp Oracle Dba MCP server in PolicyLayer and add a rule for explain_plan: 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 Oracle Dba. Nothing to install.
explain_plan is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the explain_plan 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 explain_plan. 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.
explain_plan is provided by the Mcp Oracle Dba MCP server (shopsmartai/mcp-oracle-dba). 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 →