postgres_kill_query · Multi-Database MCP Server MCP

WHAT IT DOES

What postgres_kill_query does on Multi-Database MCP Server

AI agents invoke postgres_kill_query to trigger actions in Multi-Database MCP 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 postgres_kill_query needs a policy

This tool terminates a running database query/process by its PID. While it doesn't delete data, it executes an administrative action (pg_terminate_backend) that forcibly kills a database session. This is an Execute-category action with high severity because misuse could terminate critical queries, disrupt transactions, cause application failures, or deny service to legitimate users.

From the tool's definition 'Terminate a running query by process ID' — forcibly stops an executing database process

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

postgres_kill_query Rate-limited

postgres_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": {
    "postgres_kill_query": {
      "limits": [
        {
          "counter": "postgres_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 Multi-Database MCP Server, so you can run agents against it safely.

FAQ

Questions about postgres_kill_query

What does the postgres_kill_query tool do? +

Terminate a running query by process ID (requires FULL mode). It is categorised as a Execute tool in the Multi-Database MCP 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 postgres_kill_query? +

Register the Multi-Database MCP Server MCP server in PolicyLayer and add a rule for postgres_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 Multi-Database MCP Server. Nothing to install.

What risk level is postgres_kill_query? +

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

Can I rate-limit postgres_kill_query? +

Yes. Add a rate_limit block to the postgres_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 postgres_kill_query completely? +

Set action: deny in the PolicyLayer policy for postgres_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 postgres_kill_query? +

postgres_kill_query is provided by the Multi-Database MCP Server MCP server (nam088/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.