transaction_tool · FastPostgres MCP: Risk & Policy

WHAT IT DOES

What transaction_tool does on FastPostgresMCP

AI agents invoke transaction_tool to trigger actions in FastPostgresMCP. 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_tool needs a policy

This tool executes arbitrary SQL bundles atomically against a PostgreSQL database. While transactions can be rolled back on error, successfully committed transactions may include irreversible destructive operations (DROP, DELETE, TRUNCATE).

From the tool's definition 'Execute multiple SQL statements as a single atomic transaction' — runs arbitrary SQL, potentially including DDL (DROP, TRUNCATE) or DML (DELETE, INSERT, UPDATE) statements as a batch

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

transaction_tool Rate-limited

transaction_tool 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_tool": {
      "limits": [
        {
          "counter": "transaction_tool_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 FastPostgresMCP, so you can run agents against it safely.

FAQ

Questions about transaction_tool

What does the transaction_tool tool do? +

Execute multiple SQL statements as a single atomic transaction. It is categorised as a Execute tool in the FastPostgresMCP 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_tool? +

Register the FastPostgres MCP server in PolicyLayer and add a rule for transaction_tool: 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 FastPostgresMCP. Nothing to install.

What risk level is transaction_tool? +

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

Can I rate-limit transaction_tool? +

Yes. Add a rate_limit block to the transaction_tool 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_tool completely? +

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

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