AI agents use set_niagara_float to create or update resources in Unreal — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Unreal environment.
This tool creates or modifies data (Niagara float parameters) in a reversible manner. While it affects visual effects rendering, parameter changes are not destructive—they can be undone by setting alternative values. The blast radius is medium: an AI agent could produce unintended visual effects, performance issues, or confusing VFX behavior, but cannot permanently delete assets or execute arbitrary code.
From the tool's definition Tool name 'set_niagara_float' and description 'Set a float parameter on a Niagara component' indicate modification of Niagara (VFX system) parameters. The verb 'set' modifies component state.
Attacks that exploit this kind of access
Set a float parameter on a Niagara component. It is categorised as a Write tool in the Unreal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Unreal MCP server in PolicyLayer and add a rule for set_niagara_float: 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 Unreal. Nothing to install.
set_niagara_float is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_niagara_float 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 set_niagara_float. 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.
set_niagara_float is provided by the Unreal MCP server (sam-david/unreal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →