run_luau · Dex MCP: Risk & Policy

WHAT IT DOES

What run_luau does on Dex

AI agents invoke run_luau to trigger actions in Dex. 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_luau needs a policy

This tool executes arbitrary Luau code in a Roblox client without apparent restrictions or sandboxing. While not permanently destructive by itself, arbitrary code execution in a gaming context represents critical risk: it can call game APIs to modify world state, trigger exploits, exfiltrate sensitive data, or perform actions on behalf of the user.

From the tool's definition Tool description explicitly states 'Execute arbitrary Luau in the Roblox client' and is labeled a 'Power tool'. The sibling tools (fire_remote, invoke_remote, get_properties, get_root) combined with this tool enable full control over a Roblox instance.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_luau Rate-limited

run_luau 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_luau": {
      "limits": [
        {
          "counter": "run_luau_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 Dex, so you can run agents against it safely.

FAQ

Questions about run_luau

What does the run_luau tool do? +

Execute arbitrary Luau in the Roblox client and return captured output plus a best-effort serialized return value. Power tool. It is categorised as a Execute tool in the Dex 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_luau? +

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

What risk level is run_luau? +

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

Can I rate-limit run_luau? +

Yes. Add a rate_limit block to the run_luau 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_luau completely? +

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

run_luau is provided by the Dex MCP server (sanztheo/dex-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.