remote_spy_start · Dex MCP: Risk & Policy

WHAT IT DOES

What remote_spy_start does on Dex

AI agents invoke remote_spy_start 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 remote_spy_start needs a policy

The tool activates logging machinery ('Start logging outgoing remote traffic') which requires executing hooks within the Roblox executor. While ostensibly passive (logging), it initiates executable state changes and hook installation on the client. This is more than a pure Read (which would be 'get_remote_logs').

From the tool's definition Tool description: 'Start logging outgoing remote traffic' — initiates a monitoring/logging operation that hooks into executor functionality.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

remote_spy_start Rate-limited

remote_spy_start 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": {
    "remote_spy_start": {
      "limits": [
        {
          "counter": "remote_spy_start_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 remote_spy_start

What does the remote_spy_start tool do? +

Start logging outgoing remote traffic. Returns an error if the executor lacks the required hooks. 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 remote_spy_start? +

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

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

Can I rate-limit remote_spy_start? +

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

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

remote_spy_start 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.