postgres_query · Self-hosted MCP server for Claude MCP

WHAT IT DOES

What postgres_query does on Self-hosted MCP server for Claude

AI agents invoke postgres_query to trigger actions in Self-hosted MCP server for Claude. 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_query needs a policy

This tool executes arbitrary SQL queries against a PostgreSQL database over SSH. While named 'query', it runs arbitrary SQL which could include SELECT (Read), INSERT/UPDATE (Write), DELETE/DROP (Destructive), or stored procedure calls (Execute). Since there is no stated restriction to read-only queries, it must be classified at the most severe applicable level.

From the tool's definition Run a SQL query on a PostgreSQL database — executes arbitrary SQL via psql on a remote host

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

postgres_query Rate-limited

postgres_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_query": {
      "limits": [
        {
          "counter": "postgres_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 Self-hosted MCP server for Claude, so you can run agents against it safely.

FAQ

Questions about postgres_query

What does the postgres_query tool do? +

Run a SQL query on a PostgreSQL database over SSH on a remote host from hosts.json. Uses psql via. It is categorised as a Execute tool in the Self-hosted MCP server for Claude 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_query? +

Register the Self-hosted MCP server for Claude MCP server in PolicyLayer and add a rule for postgres_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 Self-hosted MCP server for Claude. Nothing to install.

What risk level is postgres_query? +

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

Can I rate-limit postgres_query? +

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

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

postgres_query is provided by the Self-hosted MCP server for Claude MCP server (leszczynskikarol/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.