invoke_remote · Dex MCP: Risk & Policy

WHAT IT DOES

What invoke_remote does on Dex

AI agents invoke invoke_remote 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 invoke_remote needs a policy

Invoking RemoteFunction calls trigger arbitrary remote procedure execution on a Roblox server. Combined with the server's capability to 'run Luau in a Roblox client driven by an executor,' this tool enables an AI agent to execute arbitrary code on the server side with effects that depend entirely on the arguments passed.

From the tool's definition Tool invokes a RemoteFunction with arbitrary arguments (InvokeServer), which triggers server-side code execution in a Roblox environment controlled by the executor.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

invoke_remote Rate-limited

invoke_remote 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": {
    "invoke_remote": {
      "limits": [
        {
          "counter": "invoke_remote_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 invoke_remote

What does the invoke_remote tool do? +

Invoke a RemoteFunction (InvokeServer) with the given arguments and return its result. 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 invoke_remote? +

Register the Dex MCP server in PolicyLayer and add a rule for invoke_remote: 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 invoke_remote? +

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

Can I rate-limit invoke_remote? +

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

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

invoke_remote 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.