// SCAN REPORT

Unreal Mcp Ue4

34 tools. 31 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated:

31 can modify or destroy data
3 read-only
34 tools total

Verified server · catalogue entry verified 28/06/2026 · full schemas captured for 31 of 34 tools

How to control Unreal Mcp Ue4 ↓

TOOL MAP

What Unreal Mcp Ue4 exposes to your agents

Read (3) Write / Execute (30) Destructive / Financial (1)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Unreal Mcp Ue4 costs in tokens

18,953 tokens of tool definitions, loaded on every request
9.5% of a 200k context window
1,417 heaviest tool: manage_level_structure

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS
Critical Risk

The most dangerous Unreal Mcp Ue4 tools

Destructive · High editor_delete_object Delete an object/actor from the world Example output: {'success': true, 'message': 'Successfully deleted actor: MyCube', 'deleted_actor': { Write · Medium manage_widget Widget tool namespace for UMG Blueprint creation, widget-tree inspection, widget-tree edits, CanvasPanel root normalization, and viewport sp Write · Medium editor_create_object Create a new object/actor in the world Example output: {'success': true, 'actor_name': 'StaticMeshActor_1', 'actor_label': 'MyCube', 'class Write · Medium editor_update_object Update an existing object/actor in the world Example output: {'success': true, 'actor_name': 'StaticMeshActor_1', 'actor_label': 'UpdatedCu

31 of Unreal Mcp Ue4's 34 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Unreal Mcp Ue4

PolicyLayer is an MCP gateway — it sits between your AI agents and Unreal Mcp Ue4, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "editor_delete_object": {
    "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
{
  "editor_create_object": {
    "limits": [
      {
        "counter": "editor_create_object_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "get_unreal_engine_path": {
    "limits": [
      {
        "counter": "get_unreal_engine_path_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register Unreal Mcp Ue4 — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON UNREAL MCP UE4 →

Instant setup, no code required.

FULL CATALOGUE

All 34 Unreal Mcp Ue4 tools

DESTRUCTIVE 1 tools
Destructive editor_delete_object Delete an object/actor from the world Example output: {'success': true, 'message': 'Successfully deleted acto
WRITE 30 tools
Write editor_create_object Create a new object/actor in the world Example output: {'success': true, 'actor_name': 'StaticMeshActor_1', ' Write editor_update_object Update an existing object/actor in the world Example output: {'success': true, 'actor_name': 'StaticMeshActor Write manage_actor Actor tool namespace for listing, searching, spawning, deleting, transforming, and inspecting level actors. Write manage_animation_physics Animation-and-physics tool namespace for physics Blueprint spawning, Blueprint physics settings, and Blueprint Write manage_asset Asset tool namespace for listing, searching, inspecting, exporting, validating, duplicating, renaming, moving, Write manage_audio Audio tool namespace for importing audio files, searching audio assets, and inspecting their asset metadata. Write manage_behavior_tree Behavior-tree tool namespace for creating, searching, and inspecting BehaviorTree assets. Write manage_blueprint Blueprint tool namespace for Blueprint creation, component editing, compilation, and basic Blueprint summary a Write manage_data Data tool namespace for searching data assets, creating common data containers, and inspecting their asset met Write manage_editor Editor tool namespace for run_python, console_command, project_info, map_info, world_outliner, is_pie_running, Write manage_effect Effects tool namespace for spawning debug-shape actors, assigning materials, tinting them, and deleting them. Write manage_environment Environment-building tool namespace for preset town, arch, staircase, pyramid, and maze generation actions. Write manage_gas GAS tool namespace for searching gameplay-ability-related assets and inspecting their asset metadata. Write manage_geometry Geometry tool namespace for wall, arch, staircase, and pyramid preset construction actions. Write manage_input Input tool namespace for creating classic UE4 input mappings. Write manage_inspection Inspection tool namespace for asset, actor, map, and basic Blueprint summary actions. Write manage_level Level tool namespace for map inspection, actor listing, world outliner inspection, and preset structure creati Write manage_level_structure Level-structure tool namespace for preset town, house, mansion, tower, wall, bridge, and fortress construction Write manage_lighting Lighting tool namespace for spawning common light actors, transforming them, and inspecting level lighting sta Write manage_material Material tool namespace for listing materials, applying them to actors or Blueprints, and tinting them with ma Write manage_navigation Navigation tool namespace for spawning navigation volumes and proxies plus basic map inspection actions. Write manage_sequence Sequence tool namespace for creating, searching, and inspecting LevelSequence assets. Write manage_skeleton Skeleton tool namespace for searching Skeleton and SkeletalMesh assets and inspecting their metadata. Write manage_source_control Source-control tool namespace for provider inspection and file or package source-control operations. Write manage_splines Spline tool namespace for spawning a spline-host actor or Blueprint and then transforming or deleting it. Write manage_system System tool namespace for console commands and asset validation actions. Write manage_texture Texture tool namespace for searching texture assets, importing image files as textures, and reading their asse Write manage_tools Tool-namespace registry for listing registered tool namespaces and describing supported actions. Use this as t Write manage_volumes Volume tool namespace for spawning common engine volumes and applying delete or transform actions. Write manage_widget Widget tool namespace for UMG Blueprint creation, widget-tree inspection, widget-tree edits, CanvasPanel root
READ 3 tools
Read get_unreal_engine_path Get the active Unreal Engine root path from the connected editor session Read get_unreal_project_path Get the active Unreal project file path from the connected editor session Read get_unreal_version Get the active Unreal Engine version string from the connected editor session
EXPLORE

Related servers

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

Yaver 1060 tools
admin
Nodebench 824 tools
admin
Binance MCP Server 734 tools
admin
AdButler 622 tools
admin
Fortimanager 584 tools
admin
Crow 573 tools
admin
GoHighLevel MCP Server 566 tools
admin
Huly 470 tools
admin
FAQ

Questions about Unreal Mcp Ue4

Can an AI agent delete data through the Unreal Mcp Ue4 MCP server? +

Yes. The Unreal Mcp Ue4 server exposes 1 destructive tools including editor_delete_object. 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 Mcp Ue4? +

The Unreal Mcp Ue4 server has 30 write tools including editor_create_object, editor_update_object, manage_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 Mcp Ue4.

How many tools does the Unreal Mcp Ue4 MCP server expose? +

34 tools across 3 categories: Destructive, Read, Write. 3 are read-only. 31 can modify, create, or delete data.

How do I enforce a policy on Unreal Mcp Ue4? +

Register the Unreal Mcp Ue4 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 Mcp Ue4 tool call.

Deterministic rules across all 34 Unreal Mcp Ue4 tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON UNREAL MCP UE4 →

Instant setup, no code required.

34 Unreal Mcp Ue4 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.