// SCAN REPORT

Unreal

21 tools. 10 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 11 Jun 2026

10 can modify or destroy data

11 read-only

21 tools total

Community server · catalogue entry verified 11/06/2026

How to control Unreal ↓

TOOL MAP

Read (11) Write / Execute (7) Destructive / Financial (3)

MOST DANGEROUS TOOLS

Critical Risk

Destructive · High delete_actor This tool permanently removes objects from an Unreal Engine scene. Destructive · High reset_basic_castle This tool permanently removes objects from the scene without the ability to undo through the tool itself. Destructive · Medium reset_spatial_context The tool clears/resets all tracked actors in the spatial context. Execute · Low select_actors Selecting actors triggers an editor UI action/operation in Unreal Engine — it changes the editor's selection state, which is an external operation with side effects (e.g., affecting subsequent editor commands).

10 of Unreal's 21 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL UNREAL

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

Deny destructive operations

{
  "delete_actor": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "create_basic_castle": {
    "limits": [
      {
        "counter": "create_basic_castle_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_actor_info": {
    "limits": [
      {
        "counter": "get_actor_info_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 Unreal — 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 UNREAL →

Free to start. No card required.

ALL 21 UNREAL TOOLS

DESTRUCTIVE 3 tools

Destructive delete_actor Delete a specific actor from the Unreal Engine level. Destructive reset_basic_castle Delete a castle by prefix. Destructive reset_spatial_context Reset the spatial context, clearing all tracked actors.

EXECUTE 2 tools

Execute remote_call remote_call Execute select_actors Select one or more actors in the Unreal Editor.

WRITE 5 tools

Write create_basic_castle create_basic_castle Write create_static_mesh_actor create_static_mesh_actor Write modify_actor modify_actor Write save_current_level Save the currently open Unreal level. Write set_object_property set_object_property

READ 11 tools

Read get_actor_info Get detailed information about a specific actor in the Unreal Engine level. Read get_level_info Get information about the current Unreal Engine level and update spatial context. Read get_object_property get_object_property Read get_selected_actors Get the actors currently selected in the Unreal Editor. Read get_spatial_context Return the current spatial context of all actors as a JSON string. Read list_available_assets list_available_assets Read list_level_actors list_level_actors Read search_assets_recursively search_assets_recursively Read spawn_actor_from_blueprint spawn_actor_from_blueprint Read spawn_static_mesh spawn_static_mesh Read verify_basic_castle Verify that a castle built from the shared plan exists in the current level.

RELATED SERVERS

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

FAQ

Can an AI agent delete data through the Unreal MCP server? +

Yes. The Unreal server exposes 3 destructive tools including delete_actor, reset_basic_castle, reset_spatial_context. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Unreal? +

The Unreal server has 5 write tools including create_basic_castle, create_static_mesh_actor, modify_actor. 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 Unreal.

How many tools does the Unreal MCP server expose? +

21 tools across 3 categories: Destructive, Read, Write. 11 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Unreal? +

Register the Unreal 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 Unreal tool call.

Deterministic rules across all 21 Unreal tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON UNREAL →

Free to start. No card required.

21 Unreal tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

Unreal

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL UNREAL

// ALL 21 UNREAL TOOLS

// RELATED SERVERS

// FAQ