executeQuery · Postgresql MCP: Risk & Policy

WHAT IT DOES

What executeQuery does on Postgresql

AI agents invoke executeQuery to trigger actions in Postgresql. 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 executeQuery needs a policy

While the tool claims to be read-only and validates for SELECT/WITH...SELECT patterns, it executes arbitrary SQL queries against a production PostgreSQL database. SQL injection, deeply nested subqueries, or bypass of incomplete validation could cause significant load or data exposure. The truncated description reduces confidence in the actual enforcement of read-only constraints.

From the tool's definition 'Execute a read-only SQL query (SELECT, WITH...SELECT). The query is validated to ensure it doesn' — description is truncated and incomplete, limiting full assessment

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

executeQuery Rate-limited

executeQuery 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": {
    "executeQuery": {
      "limits": [
        {
          "counter": "executequery_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 Postgresql, so you can run agents against it safely.

FAQ

Questions about executeQuery

What does the executeQuery tool do? +

Execute a read-only SQL query (SELECT, WITH...SELECT). The query is validated to ensure it doesn. It is categorised as a Execute tool in the Postgresql MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on executeQuery? +

Register the Postgresql MCP server in PolicyLayer and add a rule for executeQuery: 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 Postgresql. Nothing to install.

What risk level is executeQuery? +

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

Can I rate-limit executeQuery? +

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

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

executeQuery is provided by the Postgresql MCP server (vnikhilbuddhavarapu/postgresql-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.