Gameplay systems: physics, collision, navigation, input, behavior trees, AI (EQS, perception, State Trees, Smart Objects), game framework. Actions: - set_collision_profile: Set collision preset. Params: actorLabel, profileName - set_simulate_physics: Toggle physics. Params: actorLabel, simulate -...
Risk signalsAccepts file system path (directory) · High parameter count (48 properties)
Part of the Ue server.
Free to start. No card required.
AI agents may call gameplay to permanently remove or destroy resources in Ue. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call gameplay in a loop, permanently destroying resources in Ue. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
{
"version": "1",
"default": "deny",
"hide": [
"gameplay"
]
}See the full Ue policy for all 22 tools.
These attack patterns abuse exactly the kind of access gameplay gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
Gameplay systems: physics, collision, navigation, input, behavior trees, AI (EQS, perception, State Trees, Smart Objects), game framework. Actions: - set_collision_profile: Set collision preset. Params: actorLabel, profileName - set_simulate_physics: Toggle physics. Params: actorLabel, simulate - set_collision_enabled: Set collision mode. Params: actorLabel, collisionEnabled - set_physics_properties: Set mass/damping/gravity. Params: actorLabel, mass?, linearDamping?, angularDamping?, enableGravity? - rebuild_navigation: Rebuild navmesh - find_nav_path: Synchronous nav-path query between two world points. Returns valid/partial/length plus the polyline. The standard 'why doesn't my AI move?' diagnostic. Params: start (Vec3), end (Vec3), pathfindingContext? (actorLabel - uses its agent + filter) (#424) - list_nav_invokers: Enumerate actors carrying a NavigationInvokerComponent + their tile generation/removal radii. Diagnoses 'no navmesh in this region' caused by missing or mis-sized invokers (#424) - get_navmesh_info: Query nav system - project_to_nav: Project point to navmesh. Params: location, extent? - spawn_nav_modifier: Place nav modifier. Params: location, extent?, areaClass? - list_input_assets: List input assets. Params: directory?, recursive? - list_behavior_trees: List behavior trees. Params: directory?, recursive? - get_behavior_tree_info: Inspect behavior tree (top-level + blackboard). Params: assetPath - read_behavior_tree_graph: Walk BT tree: composites, tasks, decorators, services with blackboard keys. Params: assetPath - create_blackboard: Create Blackboard. Params: name, packagePath? - add_blackboard_key: Add a typed key to a Blackboard asset. Params: blackboardPath, keyName, keyType (Bool|Int|Float|String|Name|Vector|Rotator|Object|Class|Enum), baseClass? (for Object/Class types; e.g. /Script/Engine.Actor) (#250) - set_behavior_tree_blackboard: Rebind a BehaviorTree asset's BlackboardAsset reference. Params: behaviorTreePath, blackboardPath. The C++ field is protected so reflection is the only writable path (#250) - create_behavior_tree: Create behavior tree. Params: name, packagePath?, blackboardPath? - create_eqs_query: Create EQS query. Params: name, packagePath? - list_eqs_queries: List EQS queries. Params: directory? - add_perception: Add AIPerceptionComponent. Params: blueprintPath, senses? - configure_sense: Configure perception sense. Params: blueprintPath, senseType, settings? - create_state_tree: Create StateTree. Params: name, packagePath? - list_state_trees: List StateTrees. Params: directory? - add_state_tree_component: Add StateTreeComponent. Params: blueprintPath - create_smart_object_def: Create SmartObjectDefinition. Params: name, packagePath? - add_smart_object_component: Add SmartObjectComponent. Params: blueprintPath - add_smart_object_slot: Append a FSmartObjectSlotDefinition to a SmartObjectDefinition's Slots array. Params: assetPath, name?, offset? ({x,y,z}), rotation? ({pitch,yaw,roll}), tags? (array). Returns the new slotIndex. Rollback removes the slot (#416) - set_smart_object_slot: Mutate an existing slot's offset/rotation/tags. Params: assetPath, slotIndex, offset? ({x,y,z}), rotation? ({pitch,yaw,roll}), tags? (array). Omitted fields keep their current values (#416) - remove_smart_object_slot: Remove a slot by index. Idempotent: out-of-range returns alreadyDeleted=true. Params: assetPath, slotIndex (#416) - list_smart_object_slots: List slots on a SmartObjectDefinition with index, offset, rotation, and raw text. Params: assetPath (#416) - add_smart_object_slot_behavior: Attach a behavior definition (UBehaviorDefinition asset or class) to a slot's BehaviorDefinitions array. Pass instanceProperties to seed UPROPERTYs on a freshly-spawned class-instance. Params: assetPath, slotIndex, behaviorClass (asset path or class path), instanceProperties? (#416) - create_game_mode: Create GameMode BP. Params: name, packagePath?, parentClass?, defaults? - create_game_state: Create GameState BP. Params: name, packagePath?, parentClass? - create_player_controller: Create PlayerController BP. Params: name, packagePath?, parentClass? - create_player_state: Create PlayerState BP. Params: name, packagePath? - create_hud: Create HUD BP. Params: name, packagePath? - set_world_game_mode: Set level GameMode override. Params: gameModePath - get_framework_info: Get level framework classes - get_navmesh_details: Read RecastNavMesh generation params (cellSize, agentHeight, maxStepHeight, etc.) (#163). It is categorised as a Destructive tool in the Ue MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ue MCP server in PolicyLayer and add a rule for gameplay: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Ue. Nothing to install.
gameplay is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the gameplay rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for gameplay. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
gameplay is provided by the Ue MCP server (ue-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 22 Ue tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.