kill_query · Postgres MCP: Risk & Policy

WHAT IT DOES

What kill_query does on Postgres

AI agents invoke kill_query to trigger actions in Postgres. 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 kill_query needs a policy

This tool terminates active database sessions/processes by PID. While not strictly destructive to data, it forcibly interrupts running queries and connections, which can cause transaction rollbacks, disrupt active users, and impact database availability. The 'terminate' mode (implied by 'mode=') may be more forceful than cancel.

From the tool's definition 'Cancel or terminate a backend session by PID' — kills a running database backend process

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

kill_query Rate-limited

kill_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": {
    "kill_query": {
      "limits": [
        {
          "counter": "kill_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 Postgres, so you can run agents against it safely.

FAQ

Questions about kill_query

What does the kill_query tool do? +

Cancel or terminate a backend session by PID. mode=. It is categorised as a Execute tool in the Postgres MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on kill_query? +

Register the Postgres MCP server in PolicyLayer and add a rule for kill_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 Postgres. Nothing to install.

What risk level is kill_query? +

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

Can I rate-limit kill_query? +

Yes. Add a rate_limit block to the kill_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 kill_query completely? +

Set action: deny in the PolicyLayer policy for kill_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 kill_query? +

kill_query is provided by the Postgres MCP server (teja-sudo/postgres-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.