Niagara VFX: systems, emitters, spawning, parameters, and graph authoring. Actions: - list: List Niagara assets. Params: directory?, recursive? - get_info: Inspect system. Params: assetPath - spawn: Spawn VFX. Params: systemPath, location, rotation?, label? - set_parameter: Set parameter. Params:...
Risk signalsAccepts file system path (directory) · High parameter count (37 properties)
Part of the Ue server.
Free to start. No card required.
AI agents may call niagara 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 niagara 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": [
"niagara"
]
}See the full Ue policy for all 22 tools.
These attack patterns abuse exactly the kind of access niagara 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.
Niagara VFX: systems, emitters, spawning, parameters, and graph authoring. Actions: - list: List Niagara assets. Params: directory?, recursive? - get_info: Inspect system. Params: assetPath - spawn: Spawn VFX. Params: systemPath, location, rotation?, label? - set_parameter: Set parameter. Params: actorLabel, parameterName, value, parameterType? - create: Create system. Params: name, packagePath? - create_emitter: Create Niagara emitter. Params: name, packagePath?, templatePath? - add_emitter: Add emitter to system. Params: systemPath, emitterPath - list_emitters: List emitters in system. Params: systemPath - set_emitter_property: Set emitter property. Params: systemPath, emitterName?, propertyName, value - list_modules: List Niagara modules. Params: directory? - get_emitter_info: Inspect emitter. Params: assetPath - list_renderers: List renderers on an emitter. Params: systemPath, emitterName?, emitterIndex? - add_renderer: Add renderer (sprite/mesh/ribbon or full class). Params: systemPath, rendererType, emitterName?, emitterIndex? - remove_renderer: Remove renderer by index. Params: systemPath, rendererIndex, emitterName?, emitterIndex? - set_renderer_property: Set renderer bool/number/string property. Params: systemPath, rendererIndex, propertyName, value, emitterName?, emitterIndex? - inspect_data_interfaces: List user-scope data interfaces. Params: systemPath - create_system_from_spec: Declaratively create a system + emitters. Params: name, packagePath?, emitters?:[{path}] - get_compiled_hlsl: Read GPU compute script info for an emitter. Params: systemPath, emitterName?, emitterIndex? - list_system_parameters: List user-exposed system parameters. Params: systemPath - list_module_inputs: List modules + their input pins for an emitter. Params: systemPath, emitterName?, emitterIndex?, stackContext? (ParticleSpawn|ParticleUpdate|EmitterSpawn|EmitterUpdate|all — default all) - set_module_input: Set literal default on a module input pin. Params: systemPath, moduleName, inputName, value, emitterName?, emitterIndex?, stackContext? - list_static_switches: List static switch inputs on a module. Params: systemPath, moduleName, emitterName?, emitterIndex?, stackContext? - set_static_switch: Set static switch value on a module's function call node. Params: systemPath, moduleName, switchName, value, emitterName?, emitterIndex?, stackContext? - create_module_from_hlsl: Create a NiagaraScript module backed by a custom HLSL node. Params: name, hlsl, packagePath?, inputs?:[{name,type}], outputs?:[{name,type}] - create_scratch_module: Create empty Niagara scratch module. Params: name, packagePath?, inputs?:[{name,type}], outputs?:[{name,type}] (#185) - batch: Run a sequence of niagara operations against the bridge in order. Fails fast on the first error (returns results up to that point + error). Params: ops:[{action, params}] where action is any niagara subaction listed above.. 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 niagara: 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.
niagara 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 niagara 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 niagara. 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.
niagara 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.