High-risk tools in Unreal-MCP

High severity Unreal-MCP MCP Server 13 of 286 tools

13 of the 286 tools in Unreal-MCP are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.

Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.

Tools at high risk

build_material_function_graph Execute

build_material_function_graph
build_material_graph Execute

build_material_graph
compile_blueprint Execute

Compile a Blueprint.
compile_niagara_system Execute

Compile a Niagara System and report any errors.
compile_statetree Execute

Compile a StateTree and return errors/warnings.
control_niagara_effect Execute

Control a Niagara effect actor in the level.
execute_python Execute

Execute arbitrary Python code inside the running Unreal Editor.
open_asset Execute

Open an asset in the UE5 editor (blueprint, material, data table, widget, etc.).
performance_start_trace Execute

performance_start_trace
performance_stop_trace Execute

Stop the active trace recording and optionally load it for analysis.
set_niagara_scratch_pad_hlsl Execute

set_niagara_scratch_pad_hlsl
spawn_actor_by_class Execute

spawn_actor_by_class
spawn_niagara_effect Execute

spawn_niagara_effect

Attacks that target this class

High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.

Destructive Action Autonomy
Runaway Tool Loops
Prompt Injection via Tool Results

High-risk tools in Unreal-MCP

Tools at high risk

Attacks that target this class

More on Unreal-MCP

Enforce policy on every Unreal-MCP tool call.