runQuery · MCP Oracle Server MCP: Risk & Policy

WHAT IT DOES

What runQuery does on MCP Oracle Server

AI agents invoke runQuery to trigger actions in MCP Oracle 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.

WHY IT NEEDS A POLICY

Why runQuery needs a policy

While the tool has a built-in approval requirement (approved=true) and semantic mapping guard (getSemanticMappings requirement), these are defensive controls rather than categorical changes. The tool's core function—executing SQL queries—can still perform reads, writes, updates, or potentially destructive operations depending on the SQL provided.

From the tool's definition Tool description states it 'Executes a SQL query against the Oracle database.' The action of executing arbitrary SQL queries is inherently an Execute-category operation, as it can trigger external database operations whose effects depend on the query…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

runQuery Rate-limited

runQuery 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": {
    "runQuery": {
      "limits": [
        {
          "counter": "runquery_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 Server, so you can run agents against it safely.

FAQ

Questions about runQuery

What does the runQuery tool do? +

Executes a SQL query against the Oracle database. CRITICAL SECURITY REQUIREMENT: This tool REQUIRES approved=true. It will REJECT arbitrary SQL queries. You must NOT call this tool until you have completed ALL of the following steps: 1. Call getSemanticMappings() to determine the correct table for the user. It is categorised as a Execute tool in the MCP Oracle Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on runQuery? +

Register the MCP Oracle Server MCP server in PolicyLayer and add a rule for runQuery: 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 Server. Nothing to install.

What risk level is runQuery? +

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

Can I rate-limit runQuery? +

Yes. Add a rate_limit block to the runQuery 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 runQuery completely? +

Set action: deny in the PolicyLayer policy for runQuery. 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 runQuery? +

runQuery is provided by the MCP Oracle Server MCP server (jaikishpai/mcp-server-nodejs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.