query · Pg Pool MCP: Risk & Policy

WHAT IT DOES

What query does on Pg Pool

AI agents invoke query to trigger actions in Pg Pool. 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 query needs a policy

The tool executes arbitrary SQL queries. While read-only by default, it explicitly supports write-enabled configurations, meaning it can run DML or even DDL depending on database config. The ability to execute arbitrary SQL — including potentially destructive statements — places this in the Execute category with high severity, as a misconfigured or write-enabled database could allow data modification or deletion.

From the tool's definition Execute a SQL query against a specified database. Queries are read-only by default unless the database is configured to allow writes.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query Rate-limited

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": {
    "query": {
      "limits": [
        {
          "counter": "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 Pg Pool, so you can run agents against it safely.

FAQ

Questions about query

What does the query tool do? +

Execute a SQL query against a specified database. Queries are read-only by default unless the database is configured to allow writes. It is categorised as a Execute tool in the Pg Pool MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on query? +

Register the Pg Pool MCP server in PolicyLayer and add a rule for 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 Pg Pool. Nothing to install.

What risk level is query? +

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

Can I rate-limit query? +

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

Set action: deny in the PolicyLayer policy for 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 query? +

query is provided by the Pg Pool MCP server (sam-david/pg-pool-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.