transaction · Postgresql MCP: Risk & Policy

WHAT IT DOES

What transaction does on Postgresql

AI agents invoke transaction to trigger actions in Postgresql. 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 transaction needs a policy

This tool executes arbitrary SQL statements, making it Execute category. Severity is critical because: (1) it accepts multiple SQL statements, allowing an AI to chain destructive operations (DELETE, DROP, TRUNCATE) within a single transaction; (2) atomic semantics mean errors halt execution but prior statements within the transaction still execute; (3) no mention of permissions filtering, prepared statements, or…

From the tool's definition Tool executes multiple SQL statements as atomic transactions with rollback semantics. While the server description mentions 'full read-write SQL access', this specific tool's purpose is to 'execute multiple SQL statements' with transaction control, enabling…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

transaction Rate-limited

transaction 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": {
    "transaction": {
      "limits": [
        {
          "counter": "transaction_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 Postgresql, so you can run agents against it safely.

FAQ

Questions about transaction

What does the transaction tool do? +

Execute multiple SQL statements as a single atomic transaction. Rolls back all on any error. It is categorised as a Execute tool in the Postgresql MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on transaction? +

Register the Postgresql MCP server in PolicyLayer and add a rule for transaction: 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 Postgresql. Nothing to install.

What risk level is transaction? +

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

Can I rate-limit transaction? +

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

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

transaction is provided by the Postgresql MCP server (sarmadparvez/postgresql-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.