run_select · Mcp Oracle Dba MCP: Risk & Policy

WHAT IT DOES

What run_select does on Mcp Oracle Dba

AI agents invoke run_select to trigger actions in Mcp Oracle Dba. 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.

WHY IT NEEDS A POLICY

Why run_select needs a policy

The name 'run_select' strongly implies execution of SQL SELECT queries against an Oracle database. While the server claims to be read-only with SQL guards, executing arbitrary (or semi-arbitrary) SQL queries against a database carries Execute-level risk — a misconfigured or bypassed guard could allow broader SQL execution.

From the tool's definition Tool name 'run_select' on a server described as 'SQL-guarded' with siblings like 'explain_plan' and 'top_sql'; description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_select Rate-limited

run_select stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_select": {
      "limits": [
        {
          "counter": "run_select_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Mcp Oracle Dba, so you can run agents against it safely.

FAQ

Questions about run_select

What does the run_select tool do? +

run_select. It is categorised as a Execute tool in the Mcp Oracle Dba MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_select? +

Register the Mcp Oracle Dba MCP server in PolicyLayer and add a rule for run_select: 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.

What risk level is run_select? +

run_select is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_select? +

Yes. Add a rate_limit block to the run_select 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.

How do I block run_select completely? +

Set action: deny in the PolicyLayer policy for run_select. 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.

What MCP server provides run_select? +

run_select 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.