execute_script · USQL MCP Server MCP: Risk & Policy

WHAT IT DOES

What execute_script does on USQL MCP Server

AI agents invoke execute_script to trigger actions in USQL 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 execute_script needs a policy

This tool executes arbitrary SQL scripts with potentially unrestricted effects. While not inherently destructive (category would escalate if limited to DELETE/DROP), SQL execution is fundamentally an Execute action—it can trigger external operations, modify data, or cause side effects depending on script content. The multi-statement nature and direct database forwarding amplify the blast radius.

From the tool's definition Tool name 'execute_script' combined with description 'Execute a multi-statement SQL script against a database' directly indicates code execution. Server description confirms it 'forwards queries directly to usql', enabling arbitrary SQL execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_script Rate-limited

execute_script 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": {
    "execute_script": {
      "limits": [
        {
          "counter": "execute_script_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 USQL MCP Server, so you can run agents against it safely.

FAQ

Questions about execute_script

What does the execute_script tool do? +

Execute a multi-statement SQL script against a database. It is categorised as a Execute tool in the USQL 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 execute_script? +

Register the USQL MCP Server MCP server in PolicyLayer and add a rule for execute_script: 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 USQL MCP Server. Nothing to install.

What risk level is execute_script? +

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

Can I rate-limit execute_script? +

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

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

execute_script is provided by the USQL MCP Server MCP server (jvm/usql-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.