Procedural Content Generation: graphs, nodes, connections, execution, volumes. Actions: - list_graphs: List PCG graphs. Params: directory?, recursive? - read_graph: Read graph structure. Params: assetPath - read_node_settings: Read node settings. Params: assetPath, nodeName - get_components: List...
Risk signalsAccepts file system path (directory) · High parameter count (26 properties)
Part of the Ue server.
Free to start. No card required.
AI agents may call pcg 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 pcg 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": [
"pcg"
]
}See the full Ue policy for all 22 tools.
These attack patterns abuse exactly the kind of access pcg 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.
Procedural Content Generation: graphs, nodes, connections, execution, volumes. Actions: - list_graphs: List PCG graphs. Params: directory?, recursive? - read_graph: Read graph structure. Params: assetPath - read_node_settings: Read node settings. Params: assetPath, nodeName - get_components: List PCG components in level - get_component_details: Inspect PCG component. Params: actorLabel - create_graph: Create graph. Params: name, packagePath? - add_node: Add node. Params: assetPath, nodeType, nodeName? - connect_nodes: Wire nodes. Params: assetPath, sourceNode, sourcePin, targetNode, targetPin. Returns edgeVerified=true after confirming the UPCGEdge persisted; surfaces an error if AddEdge succeeded but no edge object was instantiated (#304). - disconnect_nodes: Remove a wired edge between two PCG nodes. Params: assetPath, sourceNode, targetNode, sourcePin? (default: any), targetPin? (default: any). Returns removedEdges count (#346). - set_node_settings: Set node params. Params: assetPath, nodeName, settings - set_static_mesh_spawner_meshes: Populate weighted MeshEntries on a PCGStaticMeshSpawner node (#145). Params: assetPath, nodeName, entries=[{mesh, weight?}], replace? (default true) - remove_node: Remove node. Params: assetPath, nodeName - execute: Regenerate PCG. Params: actorLabel - force_regenerate: Force a stuck PCG component to regenerate (clears graph ref, re-sets, cleanup+generate). Params: actorLabel (#146) - cleanup: Cleanup a PCG component (remove spawned content). Params: actorLabel, removeComponents? (default true) (#146) - toggle_graph: Toggle a PCG component's graph assignment to force reinit (no generate). Params: actorLabel, graphPath? (#146) - add_volume: Place PCG volume. Params: graphPath, location?, extent? - import_graph: Bulk-author a PCG graph from JSON. Params: assetPath, nodes=[{name,class,posX?,posY?,settings?}], connections=[{from,fromPin?,to,toPin?}], replace? (default false). One call replaces N add_node + M connect_nodes + K set_node_settings (#213). - export_graph: Export a PCG graph as JSON. Params: assetPath, includeSettings? (default true). Round-trip safe with import_graph (#213).. 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 pcg: 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.
pcg 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 pcg 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 pcg. 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.
pcg 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.