execute-select-query-tool · Sql MCP: Risk & Policy

WHAT IT DOES

What execute-select-query-tool does on Sql

AI agents invoke execute-select-query-tool to trigger actions in Sql. 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 execute-select-query-tool needs a policy

Although SELECT queries themselves do not modify data, this tool fits the Execute category because it runs database queries as code operations whose effects depend on the query arguments provided by an AI agent. An agent could construct queries that trigger stored procedures, user-defined functions, or other server-side logic with unpredictable side effects.

From the tool's definition Tool description states it 'Runs parameterized SELECT queries against the database' - the verb 'Runs' combined with 'execute' in the tool name indicates code execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute-select-query-tool Rate-limited

execute-select-query-tool 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": {
    "execute-select-query-tool": {
      "limits": [
        {
          "counter": "execute-select-query-tool_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 Sql, so you can run agents against it safely.

FAQ

Questions about execute-select-query-tool

What does the execute-select-query-tool tool do? +

Runs parameterized SELECT queries against the database. It is categorised as a Execute tool in the Sql MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute-select-query-tool? +

Register the Sql MCP server in PolicyLayer and add a rule for execute-select-query-tool: 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 Sql. Nothing to install.

What risk level is execute-select-query-tool? +

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

Can I rate-limit execute-select-query-tool? +

Yes. Add a rate_limit block to the execute-select-query-tool 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 execute-select-query-tool completely? +

Set action: deny in the PolicyLayer policy for execute-select-query-tool. 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 execute-select-query-tool? +

execute-select-query-tool is provided by the Sql MCP server (prahveent/sql-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.