unreal-mcp (runreal/unreal-mcp) is an MCP server listed on the M8ven Trust Index. It scores 18 out of 100, grade F. It declares 20 tools. No publisher has claimed this listing.

F
Warning
18/100

unreal-mcp

MCP server for Unreal Engine that uses Unreal Python Remote Execution

Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

runreal

Source: mcp.so · also listed on github_topic

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Tool descriptions don’t match what handlers do
1 tool describes read intent but its handler mutates — editor_take_screenshot (line 470: fs.unlinkSync(fullPath))
⚠️
Known vulnerabilities in dependencies: 3 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
// tools this server exposes20 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

set_unreal_engine_path

Set the Unreal Engine path

set_unreal_project_path

Set the Project path

get_unreal_engine_path

Get the current Unreal Engine path

get_unreal_project_path

Get the current Unreal Project path

editor_run_python

Execute any python within the Unreal Editor. All python must have `import unreal` at the top. CHECK THE UNREAL PYTHON DOCUMENTATION BEFORE USING THIS TOOL. NEVER EVER ADD COMMENTS

editor_list_assets

List all Unreal assets Example output: [''/Game/Characters/Hero/BP_Hero'', ''/Game/Maps/TestMap'', ''/Game/Materials/M_Basic''] Returns a Python list of asset paths.

editor_export_asset

Export an Unreal asset to text Example output: Binary data of the exported asset file Returns the raw binary content of the exported asset.

editor_get_asset_info

Get information about an asset, including LOD levels for StaticMesh and SkeletalMesh assets Example output: [{'name': 'SM_Cube', 'is_valid': True, 'is_u_asset': True, 'is_asset_loaded': True, 'class': 'StaticMesh', 'path': '/Game/Meshes/SM_Cube', 'package': 'SM_Cube', 'package_path': '/Game/Meshes/

editor_get_asset_references

Get references for an asset Example output: [{'name': '/Game/Materials/M_Character.M_Character', 'class': 'Material'}, {'name': '/Game/Blueprints/BP_Player.BP_Player', 'class': 'Blueprint'}] Returns list of assets that reference the specified asset.

editor_console_command

Run a console command in Unreal Example output: (No output for most commands, executed silently) Executes the console command without returning output.

editor_project_info

Get detailed information about the current project Example output: {'project_name': 'MyGame', 'project_directory': '/Users/dev/MyGame/', 'engine_version': '5.3.0', 'total_assets': 1250, 'asset_locations': {'Game': 800, 'Engine': 450}, 'enhanced_input_enabled': true, 'input_actions': ['/Game/Input/I

editor_get_map_info

Get detailed information about the current map/level Example output: {'map_name': 'TestMap', 'map_path': '/Game/Maps/TestMap', 'total_actors': 45, 'actor_types': {'StaticMeshActor': 20, 'DirectionalLight': 1, 'PlayerStart': 1}, 'lighting': {'has_lightmass_importance_volume': false, 'directional_lig

editor_search_assets

Search for assets by name or path with optional class filter Example output: {'search_term': 'character', 'asset_class_filter': 'Blueprint', 'total_matches': 3, 'assets': [{'name': 'BP_Character', 'path': '/Game/Characters', 'class': 'Blueprint', 'package_name': 'BP_Character'}, {'name': 'BP_EnemyC

editor_get_world_outliner

Get all actors in the current world with their properties Example output: {'world_name': 'TestMap', 'total_actors': 45, 'actors': [{'name': 'StaticMeshActor_0', 'class': 'StaticMeshActor', 'location': {'x': 0.0, 'y': 0.0, 'z': 0.0}, 'rotation': {'pitch': 0.0, 'yaw': 0.0, 'roll': 0.0}, 'scale': {'x'

editor_validate_assets

Validate assets in the project to check for errors Example output: {'total_validated': 100, 'valid_assets': [{'path': '/Game/Meshes/SM_Cube', 'class': 'StaticMesh', 'size': '1024'}], 'invalid_assets': [{'path': '/Game/Missing/Asset', 'error': 'Asset does not exist'}], 'validation_summary': {'valid_

editor_create_object

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

editor_update_object

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':

editor_delete_object

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 confi

editor_take_screenshot

Take a screenshot of the Unreal Editor Example output: data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA... Returns a base64-encoded PNG image of the current editor view. IF THIS ERRORS OUT MAKE SURE THE UNREAL ENGINE WINDOW IS FOCUSED

editor_move_camera

Move the viewport camera to a specific location and rotation for positioning screenshots

// known CVEs in dependencies3 high

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.12.1GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.12.1GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.12.1GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

20/20 tools missing one or more hints — set_unreal_engine_path (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); set_unreal_project_path (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_unreal_engine_path (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +17 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Destructive tools are labelled

1 tool perform destructive updates without destructiveHint — editor_take_screenshot deletes at line 470 (fs.unlinkSync(fullPath))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — editor_take_screenshot (line 470: fs.unlinkSync(fullPath))

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool inputs are validated

16/20 tool handlers declare input schemas (80%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tests exist

No test files found

Add tests that exercise each declared tool.

No eval / new Function

1 eval() or new Function() call — dynamic code execution

Replace eval / Function with explicit parsing or safer alternatives.

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.1 (high), @modelcontextprotocol/sdk@1.12.1 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Tool description accuracy

editor_take_screenshot: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 9 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/runreal/unreal-mcp?variant=verified)](https://m8ven.ai/mcp/runreal/unreal-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 90fb0177b34b428f6e803567a4bd746974478239
code hash: 9fb645a396b6d2e770e15b889d4bb7cc5f57a9fb8eaaa5cee93e5cabe7d20d24
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client