# unreal-mcp-ue4 (npm · unreal-mcp-ue4)

UE4.27 MCP server for controlling Unreal Editor sessions over Python Remote Execution.

- Trust score: 56/100 (low)
- Change this week: +12
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `unreal-mcp-ue4`: 56/100 (this document), [markdown](https://verifymcp.io/servers/conaman-unreal-mcp-ue4/unreal-mcp-ue4.md), [page](https://verifymcp.io/servers/conaman-unreal-mcp-ue4/unreal-mcp-ue4)

## Channel facts

- Registry: `npm`
- Package: `unreal-mcp-ue4`
- Version: `2026.4.1-2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 83 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 27/100
  - 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (poor).
  - Tool/resource definitions use about 2266 tokens (~64/item across 35 items; 34 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 99% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add conaman-unreal-mcp-ue4 -- npx -y unreal-mcp-ue4
```

### Codex

```bash
codex mcp add conaman-unreal-mcp-ue4 -- npx -y unreal-mcp-ue4
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "conaman-unreal-mcp-ue4": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "unreal-mcp-ue4"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add conaman-unreal-mcp-ue4 --command npx --arg -y --arg unreal-mcp-ue4
```

### Hermes

```yaml
mcp_servers:
  conaman-unreal-mcp-ue4:
    command: "npx"
    args: ["-y", "unreal-mcp-ue4"]
```

### Other

```json
{
  "mcpServers": {
    "conaman-unreal-mcp-ue4": {
      "command": "npx",
      "args": [
        "-y",
        "unreal-mcp-ue4"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 56, +8)

- [security regression] Install scripts: pass → unverified
- [security regression] Provenance: fail → unverified
- [security improvement] Known CVEs: unverified → partial
- [functional regression] Maintenance: pass → unverified
- [functional regression] License: pass → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: MIT

### 2026-08-01 (score 48, −11)

- [security regression] Known CVEs: partial → unverified
- [functional regression] Dependency health: partial → unverified

### 2026-07-31 (score 59, +24)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 35, +10)

- [security regression] Provenance: unverified → fail
- [security regression] Malware scan: pass → unverified
- [security improvement] Install scripts: unverified → pass
- [functional regression] Security disclosure: unverified → fail
- [functional regression] Dependency health: partial → unverified
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] License: unverified → pass
- [functional improvement] Schema quality: unverified → 0
- [functional improvement] Maintenance: unverified → pass
- [functional] Licence: MIT

### 2026-07-29 (score 25, −19)

- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 0 → unverified
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Dependency health: unverified → partial

### 2026-07-27 (score 44)

First indexed and scored.

## MCP tools (34)

### `get_unreal_engine_path` (~24 tokens)

Get the active Unreal Engine root path from the connected editor session

### `get_unreal_project_path` (~24 tokens)

Get the active Unreal project file path from the connected editor session

### `get_unreal_version` (~23 tokens)

Get the active Unreal Engine version string from the connected editor session

### `editor_create_object` (~279 tokens)

Create a new object/actor in the world

Example output: {'success': true, 'actor_name': 'StaticMeshActor_1', 'actor_label': 'MyCube', 'class': 'StaticMeshActor', 'location': {'x': 100.0, 'y': 200.0, 'z': 0.0}, 'rotation': {'pitch': 0.0, 'yaw': 45.0, 'roll': 0.0}, 'scale': {'x': 1.0, 'y': 1.0, 'z': 1.0}}

Returns created actor details with final transform values.

Input parameters:

- `location` (object): World position coordinates
- `object_class` (string, required): Unreal class name (e.g., 'StaticMeshActor', 'DirectionalLight')
- `object_name` (string, required): Name/label for the created object
- `properties` (object): Additional actor properties. For StaticMeshActor: use 'StaticMesh' for mesh path, 'Material' for single material path, or 'Materials' for array of material paths. Example: {"StaticMesh": "/Game/Meshe…
- `rotation` (object): Rotation in degrees
- `scale` (object): Scale multipliers

### `editor_update_object` (~277 tokens)

Update an existing object/actor in the world

Example output: {'success': true, 'actor_name': 'StaticMeshActor_1', 'actor_label': 'UpdatedCube', 'class': 'StaticMeshActor', 'location': {'x': 150.0, 'y': 200.0, 'z': 50.0}, 'rotation': {'pitch': 0.0, 'yaw': 90.0, 'roll': 0.0}, 'scale': {'x': 2.0, 'y': 2.0, 'z': 2.0}}

Returns updated actor details with new transform values.

Input parameters:

- `actor_name` (string, required): Name or label of the actor to update
- `location` (object): New world position coordinates
- `new_name` (string): New name/label for the actor
- `properties` (object): Additional actor properties to update. For StaticMeshActor: use 'StaticMesh' for mesh path, 'Material' for single material path, or 'Materials' for array of material paths. Example: {"StaticMesh": "/…
- `rotation` (object): New rotation in degrees
- `scale` (object): New scale multipliers

### `editor_delete_object` (~114 tokens)

Delete an object/actor from the world

Example output: {'success': true, 'message': 'Successfully deleted actor: MyCube', 'deleted_actor': {'actor_name': 'StaticMeshActor_1', 'actor_label': 'MyCube', 'class': 'StaticMeshActor', 'location': {'x': 100.0, 'y': 200.0, 'z': 0.0}}}

Returns deletion confirmation with details of the deleted actor.

Input parameters:

- `actor_names` (string, required)

### `manage_asset` (~52 tokens)

Asset tool namespace for list, search, info, references, export, and validation actions.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_asset
- `params` (object): Optional action parameter object

### `manage_actor` (~53 tokens)

Actor tool namespace for listing, searching, spawning, deleting, transforming, and inspecting level actors.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_actor
- `params` (object): Optional action parameter object

### `manage_editor` (~59 tokens)

Editor tool namespace for Python execution, console commands, project inspection, map inspection, PIE control, screenshots, and camera control.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_editor
- `params` (object): Optional action parameter object

### `manage_system` (~45 tokens)

System tool namespace for console commands and asset validation actions.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_system
- `params` (object): Optional action parameter object

### `manage_inspection` (~52 tokens)

Inspection tool namespace for asset, actor, map, and basic Blueprint summary actions.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_inspection
- `params` (object): Optional action parameter object

### `manage_tools` (~62 tokens)

Tool-namespace registry for listing registered tool namespaces and describing supported actions. Use this as the discovery entry point for the namespace-first MCP surface.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_tools
- `params` (object): Optional action parameter object

### `manage_source_control` (~51 tokens)

Source-control tool namespace for provider inspection and file or package source-control operations.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_source_control
- `params` (object): Optional action parameter object

### `manage_lighting` (~54 tokens)

Lighting tool namespace for spawning common light actors, transforming them, and inspecting level lighting state.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_lighting
- `params` (object): Optional action parameter object

### `manage_volumes` (~51 tokens)

Volume tool namespace for spawning common engine volumes and applying delete or transform actions.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_volumes
- `params` (object): Optional action parameter object

### `manage_navigation` (~49 tokens)

Navigation tool namespace for spawning navigation volumes and proxies plus basic map inspection actions.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_navigation
- `params` (object): Optional action parameter object

### `manage_splines` (~57 tokens)

Spline tool namespace for spawning a spline-host actor or Blueprint and then transforming or deleting it.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_splines
- `params` (object): Optional action parameter object

### `manage_effect` (~55 tokens)

Effects tool namespace for spawning debug-shape actors, assigning materials, tinting them, and deleting them.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_effect
- `params` (object): Optional action parameter object

### `manage_level` (~55 tokens)

Level tool namespace for map inspection, actor listing, world outliner inspection, and preset structure creation actions.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_level
- `params` (object): Optional action parameter object

### `manage_level_structure` (~60 tokens)

Level-structure tool namespace for preset town, house, mansion, tower, wall, bridge, and fortress construction actions.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_level_structure
- `params` (object): Optional action parameter object

### `manage_environment` (~53 tokens)

Environment-building tool namespace for preset town, arch, staircase, pyramid, and maze generation actions.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_environment
- `params` (object): Optional action parameter object

### `manage_geometry` (~50 tokens)

Geometry tool namespace for wall, arch, staircase, and pyramid preset construction actions.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_geometry
- `params` (object): Optional action parameter object

### `manage_skeleton` (~52 tokens)

Skeleton tool namespace for searching Skeleton and SkeletalMesh assets and inspecting their metadata.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_skeleton
- `params` (object): Optional action parameter object

### `manage_material` (~57 tokens)

Material tool namespace for listing materials, applying them to actors or Blueprints, and tinting them with material instances.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_material
- `params` (object): Optional action parameter object

### `manage_texture` (~54 tokens)

Texture tool namespace for searching texture assets, importing image files as textures, and reading their asset metadata.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_texture
- `params` (object): Optional action parameter object

### `manage_data` (~53 tokens)

Data tool namespace for searching data assets, creating common data containers, and inspecting their asset metadata.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_data
- `params` (object): Optional action parameter object

### `manage_blueprint` (~54 tokens)

Blueprint tool namespace for Blueprint creation, component editing, compilation, and basic Blueprint summary actions.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_blueprint
- `params` (object): Optional action parameter object

### `manage_widget` (~87 tokens)

Widget tool namespace for UMG Blueprint creation, widget-tree edits, and viewport spawning actions. Use add_child_widget for typical nested layout work under an existing root such as CanvasPanel_0; add_widget without parent_widget_name is only for assigning a new root widget.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_widget
- `params` (object): Optional action parameter object

### `manage_sequence` (~48 tokens)

Sequence tool namespace for creating, searching, and inspecting LevelSequence assets.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_sequence
- `params` (object): Optional action parameter object

### `manage_audio` (~52 tokens)

Audio tool namespace for importing audio files, searching audio assets, and inspecting their asset metadata.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_audio
- `params` (object): Optional action parameter object

### `manage_animation_physics` (~58 tokens)

Animation-and-physics tool namespace for physics Blueprint spawning, Blueprint physics settings, and Blueprint compilation actions.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_animation_physics
- `params` (object): Optional action parameter object

### `manage_input` (~45 tokens)

Input tool namespace for creating classic UE4 input mappings.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_input
- `params` (object): Optional action parameter object

### `manage_behavior_tree` (~51 tokens)

Behavior-tree tool namespace for creating, searching, and inspecting BehaviorTree assets.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_behavior_tree
- `params` (object): Optional action parameter object

### `manage_gas` (~52 tokens)

GAS tool namespace for searching gameplay-ability-related assets and inspecting their asset metadata.

Input parameters:

- `action` (string, required): Action to execute inside tool namespace manage_gas
- `params` (object): Optional action parameter object

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/conaman-unreal-mcp-ue4/unreal-mcp-ue4#diagnostics

## Score history

- 2026-08-03: 56
- 2026-08-02: 56
- 2026-08-01: 48
- 2026-07-31: 59
- 2026-07-30: 35
- 2026-07-29: 25
- 2026-07-28: 44
- 2026-07-27: 44

## Links

- npm package: https://www.npmjs.com/package/unreal-mcp-ue4
- Socket report: https://socket.dev/npm/package/unreal-mcp-ue4
- Repository: https://github.com/conaman/unreal-mcp-ue4
- Changelog RSS feed: https://verifymcp.io/servers/conaman-unreal-mcp-ue4/unreal-mcp-ue4/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/conaman-unreal-mcp-ue4/unreal-mcp-ue4/changelog.json
- HTML version of this page: https://verifymcp.io/servers/conaman-unreal-mcp-ue4/unreal-mcp-ue4