// SCAN REPORT

Dex

14 tools. 6 can modify or destroy data without limits.

6 write tools that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

6 can modify or destroy data

8 read-only

14 tools total

Community server · catalogue entry verified 02/07/2026

How to control Dex ↓

TOOL MAP

What Dex exposes to your agents

Read (8) Write / Execute (6) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Dex tools

Execute · Critical invoke_remote Invoking RemoteFunction calls trigger arbitrary remote procedure execution on a Roblox server. Execute · High remote_spy_start The tool activates logging machinery ('Start logging outgoing remote traffic') which requires executing hooks within the Roblox executor. Execute · Medium remote_spy_stop While this tool appears to only stop logging (non-destructive), it is classified as Execute rather than Write because it triggers a state-change action on an active system process rather than modifying persistent data. Execute · Critical run_luau This tool executes arbitrary Luau code in a Roblox client without apparent restrictions or sandboxing.

6 of Dex's 14 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Dex

PolicyLayer is an MCP gateway — it sits between your AI agents and Dex, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "set_property": {
    "limits": [
      {
        "counter": "set_property_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "dex_status": {
    "limits": [
      {
        "counter": "dex_status_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Dex — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON DEX →

Instant setup, no code required.

FULL CATALOGUE

All 14 Dex tools

EXECUTE 5 tools

Execute fire_remote Fire a RemoteEvent (FireServer) with the given arguments. Execute invoke_remote Invoke a RemoteFunction (InvokeServer) with the given arguments and return its result. Execute remote_spy_start Start logging outgoing remote traffic. Returns an error if the executor lacks the required hooks. Execute remote_spy_stop Stop logging remote traffic. Execute run_luau Execute arbitrary Luau in the Roblox client and return captured output plus a best-effort serialized return va

WRITE 1 tools

Write set_property Set a property on an instance by ref. The value is coerced to the property

READ 8 tools

Read dex_status Report whether the Roblox bridge is connected and basic game info (name, placeId, client version, capabilities Read get_by_path Resolve a dotted instance path (e.g. game.Workspace.Part) to a node with a ref. Read get_children List the direct children of an instance by ref. Optionally filter by className. Read get_properties Read the properties of an instance by ref. Property names come from the cached Roblox API dump when available. Read get_root Get the root instance (game, ref 0) and its top-level services. Read get_source Read the Source of a Script/LocalScript/ModuleScript by ref, if readable. Read remote_spy_dump Return the remote traffic captured since the spy started. Read search Recursively search instances by name substring (and optional className), capped by limit. Defaults to 100 resu

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Dex

How do I prevent bulk modifications through Dex? +

The Dex server has 1 write tools including set_property. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Dex.

How many tools does the Dex MCP server expose? +

14 tools across 3 categories: Execute, Read, Write. 8 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Dex? +

Register the Dex MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Dex tool call.

Deterministic rules across all 14 Dex tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DEX →

Instant setup, no code required.

14 Dex tools catalogued and risk-classified — across an index of 43,000+ MCP servers.