blueprint

// WHEN AI AGENTS USE THIS TOOL

AI agents may call blueprint 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. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.

// WHY ENFORCE A POLICY ON BLUEPRINT

Without a policy, an AI agent could call blueprint in a loop, permanently destroying resources in Ue. There is no undo for destructive operations. Intercept blocks this tool by default and only allows it when a human explicitly approves the action.

// RECOMMENDED POLICY

Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.

ue.yaml

tools:
  blueprint:
    rules:
      - action: deny
        reason: "Blocked by default — enable with approval"

See the full Ue policy for all 20 tools.

// DETAILS

Tool Name blueprint

Category Destructive

MCP Server Ue MCP Server

Risk Level Critical

// MORE UE TOOLS

Destructive animation Destructive asset Destructive demo Destructive editor Destructive foliage Destructive gameplay Destructive level Destructive material

View all 20 tools →

// WHAT CAN GO WRONG

Agents calling destructive-class tools like blueprint have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER DESTRUCTIVE TOOLS ACROSS MCP SERVERS

Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.

AbraFlexi contact_delete AbraFlexi evidence_delete AbraFlexi invoice_issued_delete AbraFlexi product_delete Agent Passport System — Cryptographic Identity for AI Agents remove_intent_card Agent Passport System — Cryptographic Identity for AI Agents revoke_delegation

// IN CONTEXT OF CRITICAL RISK

blueprint is one of the critical-risk operations in Ue. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.

// RELATED READING

// FAQ

What does the blueprint tool do? +

Blueprint reading, authoring, and compilation. Covers variables, functions, graphs, nodes, components, interfaces, and event dispatchers. Actions: - read: Read BP structure incl. SCS components. Params: assetPath - list_variables: List variables. Params: assetPath - list_functions: List functions/graphs. Params: assetPath - read_graph: Read graph nodes. Params: assetPath, graphName - read_graph_summary: Lightweight graph summary (nodes+edges only, ~10KB). Params: assetPath, graphName? - get_execution_flow: Trace exec pins from an entry point. Params: assetPath, graphName?, entryPoint? - get_dependencies: Forward (classes/functions/assets) or reverse (referencers) deps. Params: assetPath, reverse? - create: Create Blueprint. Params: assetPath, parentClass? - add_variable: Add variable. Params: assetPath, name, varType - set_variable_properties: Edit variable properties. Params: assetPath, name, instanceEditable?, blueprintReadOnly?, category?, tooltip?, replicationType? - create_function: Create function. Params: assetPath, functionName - delete_function: Delete function. Params: assetPath, functionName - rename_function: Rename function. Params: assetPath, oldName, newName - add_node: Add graph node. Params: assetPath, graphName?, nodeClass, nodeParams? - delete_node: Delete node. Params: assetPath, graphName, nodeName - set_node_property: Set node pin default or struct property. Params: assetPath, graphName, nodeName, propertyName, value - connect_pins: Wire nodes. Params: sourceNode, sourcePin, targetNode, targetPin, assetPath, graphName? - add_component: Add BP component. Params: assetPath, componentClass, componentName?, parentComponent? (SCS parent for hierarchy — #115) - remove_component: Remove SCS component. Params: assetPath, componentName - set_component_property: Set property on SCS or inherited component. Inherited components go through the child BP's InheritableComponentHandler override template so the parent stays untouched. Params: assetPath, componentName, propertyName, value - get_component_property: Read a single property value from an SCS or inherited component template. Returns the ICH override value for child BPs if one exists. Params: assetPath, componentName, propertyName - set_class_default: Set UPROPERTY on Blueprint CDO. Params: assetPath, propertyName, value - delete_variable: Delete a member variable. Params: assetPath, name - add_function_parameter: Add input or output parameter to a function. Params: assetPath, functionName, parameterName, parameterType?, isOutput? - set_variable_default: Set default value on a BP variable. Params: assetPath, name, value - compile: Compile Blueprint. Params: assetPath - list_node_types: List node types. Params: category?, includeFunctions? - search_node_types: Search nodes. Params: query - create_interface: Create BP Interface. Params: assetPath - add_interface: Implement interface. Params: blueprintPath, interfacePath - list_graphs: List all graphs in a blueprint. Params: assetPath - add_event_dispatcher: Add event dispatcher. Params: blueprintPath, name - duplicate: Duplicate blueprint asset. Params: sourcePath, destinationPath - add_local_variable: Add function-scope local variable. Params: assetPath, functionName, name, varType? - list_local_variables: List local variables in a function. Params: assetPath, functionName - validate: Validate blueprint without saving (compile + collect diagnostics). Params: assetPath - read_component_properties: Dump ALL UPROPERTYs on a BP component template incl. array contents (#105). Params: assetPath, componentName - read_node_property: Read a node pin default OR a reflected node property for verification (#102). Params: assetPath, graphName?, nodeName, propertyName - reparent_component: Reparent an SCS component under a new parent (#115). Params: assetPath, componentName, newParent - reparent: Change a Blueprint's ParentClass and recompile (#138). Params: assetPath, parentClass (short name or full path). - set_actor_tick_settings: Set actor CDO tick settings (#116). Params: assetPath, bCanEverTick?, bStartWithTickEnabled?, TickInterval? - export_nodes_t3d: Export graph nodes as T3D text (Ctrl+C equivalent) for bulk round-trip (#130). Params: assetPath, graphName?, nodeIds? (omit = whole graph) - import_nodes_t3d: Paste a T3D node blob into a graph (Ctrl+V equivalent) for bulk authoring (#130). Params: assetPath, graphName?, t3d, posX?, posY?. 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.

How do I enforce a policy on blueprint? +

Add a rule in your Intercept YAML policy under the tools section for blueprint. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Ue MCP server.

What risk level is blueprint? +

blueprint is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit blueprint? +

Yes. Add a rate_limit block to the blueprint rule in your Intercept 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.

How do I block blueprint completely? +

Set action: deny in the Intercept policy for blueprint. 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.

What MCP server provides blueprint? +

blueprint is provided by the Ue MCP server (ue-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Ue