Top SQL by elapsed time from v$sql within the last N minutes.
AI agents call top_sql to retrieve information from Mcp Oracle Dba without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves performance diagnostic data from Oracle's dynamic performance views. It has no capability to modify, delete, or execute arbitrary code—it only reads and reports SQL statistics. The read-only server architecture and absence of any write/execute/delete operations confirm Read classification.
From the tool's definition Tool queries v$sql view to retrieve SQL performance metrics; description explicitly states 'Top SQL by elapsed time' which is a data retrieval operation with no modification capability.
Attacks that exploit this kind of access
Top SQL by elapsed time from v$sql within the last N minutes. 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 top_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 Mcp Oracle Dba. Nothing to install.
top_sql 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 top_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 top_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.
top_sql 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 →