run_custom_sql · Google Services MCP Server MCP

WHAT IT DOES

What run_custom_sql does on Google Services MCP Server

AI agents invoke run_custom_sql to trigger actions in Google Services 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 run_custom_sql needs a policy

This tool allows execution of arbitrary SQL commands with no restrictions mentioned. While it spans multiple categories (Write for INSERT/UPDATE, Destructive for DELETE), Execute is the appropriate classification because the tool's primary function is to run code (SQL) whose consequences are determined by the argument.

From the tool's definition "Execute any SQL query (SELECT, INSERT, UPDATE, DELETE, etc.)" — the tool explicitly permits arbitrary SQL execution including INSERT, UPDATE, and DELETE operations whose effects depend entirely on the query argument provided by the AI agent.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_custom_sql Rate-limited

run_custom_sql 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": {
    "run_custom_sql": {
      "limits": [
        {
          "counter": "run_custom_sql_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 Google Services MCP Server, so you can run agents against it safely.

FAQ

Questions about run_custom_sql

What does the run_custom_sql tool do? +

Execute any SQL query (SELECT, INSERT, UPDATE, DELETE, etc.). Automatically handles query type. It is categorised as a Execute tool in the Google Services 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 run_custom_sql? +

Register the Google Services MCP Server MCP server in PolicyLayer and add a rule for run_custom_sql: 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 Google Services MCP Server. Nothing to install.

What risk level is run_custom_sql? +

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

Can I rate-limit run_custom_sql? +

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

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

run_custom_sql is provided by the Google Services MCP Server MCP server (t4nm4ymittal/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.