unreal-mcp (sam-david/unreal-mcp) is an MCP server listed on the M8ven Trust Index. It scores 50 out of 100, grade D. It declares 127 tools. No publisher has claimed this listing.

D
Caution
50/100

unreal-mcp

Enables natural language interaction with Unreal Engine, providing 127 tools across 16 subsystems for tasks like actor manipulation, asset management, blueprint creation, and more, using built-in Python and Remote Control plugins.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code 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

sam-david

Source: Glama

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
🚨
Known vulnerabilities in dependencies: 2 critical, 4 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
// tools this server exposes127 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.

list_actors

List all actors in the current level, optionally filtered by class.

spawn_actor

Spawn a new actor in the current level.

delete_actor

Delete an actor from the current level by name or label.

get_actor_properties

Get all properties of an actor by name.

set_actor_transform

Set the location, rotation, and/or scale of an actor.

set_actor_property

Set a property on an actor via the Remote Control API.

get_actor_components

List all components on an actor.

select_actors

Set the editor's actor selection.

duplicate_actors

Duplicate actors by name.

set_actor_tags

Set tags on an actor.

create_anim_blueprint

Create an Animation Blueprint for a target skeleton.

get_anim_sequence_info

Get info about an animation sequence (length, frames, bone data).

create_anim_montage

Create an animation montage from an animation sequence.

set_skeletal_mesh_lod

Configure LOD settings on a skeletal mesh.

reimport_skeletal_mesh

Reimport a skeletal mesh from its source file.

apply_anim_modifier

Apply an animation modifier to an animation sequence.

list_assets

List assets in a content directory with optional class filter.

search_assets

Search for assets by name, class, or tag.

get_asset_info

Get detailed metadata for an asset.

get_asset_references

Get the dependency and referencer graph for an asset.

rename_asset

Rename or move an asset.

duplicate_asset

Duplicate an asset to a new path.

delete_asset

Delete an asset. Checks for references first.

import_asset

Import an external file (FBX, PNG, WAV, etc.) into the project.

export_asset

Export an asset to an external file format.

validate_assets

Run data validation on assets in a directory.

save_asset

Force save a specific asset.

save_all

Save all dirty (modified) assets.

fix_redirectors

Clean up asset redirectors in the project (runs FixUpRedirects commandlet).

resave_packages

Bulk resave all packages in the project (runs ResavePackages commandlet).

content_audit

Run content audit to find costly or problematic assets (runs ContentAudit commandlet).

consolidate_assets

Consolidate duplicate assets — replace references from source assets to a target asset.

create_blueprint

Create a new Blueprint class.

add_blueprint_component

Add a component to a Blueprint.

add_blueprint_variable

Add a variable to a Blueprint.

add_graph_node

Add a node to a Blueprint's event graph. Requires the optional C++ plugin for full node type support. Falls back to Python for basic operations.

connect_graph_nodes

Wire two node pins together in a Blueprint graph. Requires the optional C++ plugin.

remove_graph_node

Remove a node from a Blueprint graph. Requires the optional C++ plugin.

list_graph_nodes

List all nodes in a Blueprint's event graph.

compile_blueprint

Compile a Blueprint.

get_blueprint_info

Get Blueprint info: class, variables, functions, components, and graphs.

spawn_blueprint_actor

Spawn an instance of a Blueprint class in the level.

add_blueprint_function

Add a custom function to a Blueprint.

set_blueprint_property

Set a default property value on a Blueprint's CDO (Class Default Object). For component properties, use a dot path like 'ComponentName.PropertyName'.

build_target

Build a C++ target using UnrealBuildTool. Compiles the project's C++ code.

build_cook_run

Full BuildCookRun pipeline — build, cook, stage, package, and optionally deploy/run. This is the primary command for packaging a project.

cook_content

Cook content only (no C++ build). Converts assets to platform-specific format.

package_project

Package the project for distribution. Runs build + cook + stage + package.

build_plugin

Build a plugin standalone.

generate_project_files

Regenerate IDE project files (Visual Studio, Xcode, Rider).

build_graph

Execute a BuildGraph XML script for CI/CD automation.

clean_project

Clean build artifacts for the project.

get_build_status

Parse the last build output and return structured errors, warnings, and progress.

execute_python

Execute arbitrary Python code in the Unreal Editor's Python environment. Has access to the full `unreal` module.

execute_console_command

Run a console command in the Unreal Editor (e.g., 'stat fps', 'stat unit', 'r.SetRes 1920x1080').

take_screenshot

Capture a screenshot of the active editor viewport. Returns the file path of the saved image.

get_viewport_camera

Get the current editor viewport camera location and rotation.

set_viewport_camera

Set the editor viewport camera location and/or rotation.

get_connection_status

Check which Unreal Engine transports are currently connected (Remote Control, Python, Plugin Bridge).

run_editor_utility_widget

Run an Editor Utility Widget by asset path.

run_editor_utility_blueprint

Run an Editor Utility Blueprint's Run event.

generate_lods

Generate LODs for a static mesh.

generate_collision

Generate collision for a static mesh.

generate_lightmap_uvs

Generate lightmap UVs for a static mesh.

undo

Undo the last editor action.

redo

Redo the last undone editor action.

get_undo_history

Get the undo/redo transaction history.

create_material

Create a new material asset.

apply_material

Apply a material to an actor's mesh component.

create_material_expression

Add an expression node to a material's graph (e.g., TextureSample, Multiply, Constant3Vector).

connect_material_expressions

Wire two material expression nodes together.

connect_material_property

Connect an expression to a material output property (BaseColor, Normal, Metallic, Roughness, etc.).

delete_material_expression

Remove an expression node from a material graph.

list_material_expressions

List all expression nodes in a material.

create_material_instance

Create a material instance from a parent material.

set_material_instance_scalar

Set a scalar parameter on a material instance.

set_material_instance_vector

Set a vector parameter on a material instance.

set_material_instance_texture

Set a texture parameter on a material instance.

recompile_material

Recompile a material after making changes to its graph.

create_material_function

Create a reusable material function.

spawn_niagara_at_location

Spawn a Niagara particle system at a world location.

spawn_niagara_attached

Spawn a Niagara system attached to an actor.

set_niagara_float

Set a float parameter on a Niagara component.

set_niagara_vector

Set a vector parameter on a Niagara component.

set_niagara_color

Set a linear color parameter on a Niagara component.

set_niagara_bool

Set a bool parameter on a Niagara component.

reset_niagara_system

Reset a Niagara system on an actor.

reinit_niagara_system

Reinitialize a Niagara system on an actor.

list_plugins

List installed plugins and their enabled status.

enable_plugin

Enable a plugin in the .uproject file. Requires editor restart to take effect.

disable_plugin

Disable a plugin in the .uproject file. Requires editor restart to take effect.

start_trace

Start an Unreal Insights trace session with selected channels.

stop_trace

Stop the active Unreal Insights trace session.

run_stat_command

Execute a stat console command (e.g., stat fps, stat unit, stat memory).

start_csv_profiling

Start CSV profiling capture for performance regression analysis.

stop_csv_profiling

Stop CSV profiling capture and save results.

list_presets

List all Remote Control Presets in the project.

get_preset_info

Get details of a Remote Control Preset (exposed properties and functions).

get_preset_property

Get a property value exposed via a Remote Control Preset.

set_preset_property

Set a property value exposed via a Remote Control Preset.

27 further tools are not listed here. The complete surface is in the source.

// known CVEs in dependencies2 critical4 high1 low

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

criticalvitest@3.0.0GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

criticalvitest@3.0.0GHSA-9crc-q9x8-hgqq

Vitest allows Remote Code Execution when accessing a malicious website while Vitest API server is listening

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 →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configUNREAL_MCP_CONFIGURATIONDevelopment Build configuration
configUNREAL_MCP_ENGINE_PATHauto-detect UE engine install path
configUNREAL_MCP_MODULESall Comma-separated list of modules to enable
configUNREAL_MCP_PLATFORMWin64 Target platform
configUNREAL_MCP_PROJECT_PATH"": "/path/to/YourProject.uproject"
configUNREAL_MCP_PYTHON_PORT6776 Python Remote Execution port
configUNREAL_MCP_RC_PORT30010 Remote Control API port
// 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

127/127 tools missing one or more hints — list_actors (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); spawn_actor (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); delete_actor (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +124 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.

Tool inputs are validated

104/127 tool handlers declare input schemas (82%)

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

Tool handlers catch errors

Only 0/127 tool handlers wrap calls in try/catch (0%)

Wrap each tool handler body in try/catch and return a structured error response.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tests exist

No test files found

Add tests that exercise each declared tool.

Shell command execution

8 child_process calls — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Production dependencies are patched

0 critical, 4 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.

Dev dependencies

2 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

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/sam-david/unreal-mcp?variant=verified)](https://m8ven.ai/mcp/sam-david/unreal-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 8b88ec3a79f74e90e8ddb0509cc8f68f8ab22011
code hash: b0ae2badb7f2a2dff121b9b2b196073a3043c0b3f33710acd5a735f8a8f908ae
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