execute_select_query · MCP PostgreSQL Read-Only Server MCP

WHAT IT DOES

What execute_select_query does on MCP PostgreSQL Read-Only Server

AI agents invoke execute_select_query to trigger actions in MCP PostgreSQL Read-Only 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 execute_select_query needs a policy

Although the server is described as read-only and restricted to SELECT, executing arbitrary custom SQL queries is an Execute-category action. A misused or poorly sanitised query could exfiltrate large volumes of sensitive data, cause heavy load, or (if enforcement is weak) bypass restrictions.

From the tool's definition 'Ejecuta una consulta SELECT personalizada' (executes a custom SELECT query) — arbitrary user-supplied SQL is run against the database

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_select_query Rate-limited

execute_select_query 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": {
      "limits": [
        {
          "counter": "execute_select_query_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 PostgreSQL Read-Only Server, so you can run agents against it safely.

FAQ

Questions about execute_select_query

What does the execute_select_query tool do? +

Ejecuta una consulta SELECT personalizada en la base de datos PostgreSQL. It is categorised as a Execute tool in the MCP PostgreSQL Read-Only 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 execute_select_query? +

Register the MCP PostgreSQL Read-Only Server MCP server in PolicyLayer and add a rule for execute_select_query: 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 PostgreSQL Read-Only Server. Nothing to install.

What risk level is execute_select_query? +

execute_select_query 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? +

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

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

execute_select_query is provided by the MCP PostgreSQL Read-Only Server MCP server (japentaca/mcp-postgres-readonly). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.