update_rows · Postgres MCP: Risk & Policy

WHAT IT DOES

What update_rows does on Postgres

AI agents use update_rows to create or update resources in Postgres — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Postgres environment.

WHY IT NEEDS A POLICY

Why update_rows needs a policy

This tool modifies existing data in a PostgreSQL database. It is categorized as Write rather than Execute because while it executes SQL, its primary purpose is reversible data modification (UPDATE), not arbitrary code execution. The severity is high because unrestricted updates could modify critical business data across multiple rows, causing significant operational impact.

From the tool's definition UPDATE rows matching a WHERE clause and return affected records - performs reversible modification of database records via UPDATE statement

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_rows Rate-limited

update_rows stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "update_rows": {
      "limits": [
        {
          "counter": "update_rows_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 update_rows

What does the update_rows tool do? +

UPDATE rows matching a WHERE clause and return affected records. It is categorised as a Write tool in the Postgres MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_rows? +

Register the Postgres MCP server in PolicyLayer and add a rule for update_rows: 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 update_rows? +

update_rows is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit update_rows? +

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

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

update_rows is provided by the Postgres MCP server (santisanti13/postgres-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.