Epic's native Unreal 5.8 AI Toolset Registry, wrapped as first-class actions. Every toolset Epic ships (GAS, Niagara, PCG, UMG, StateTree, editor actor/asset/blueprint, sequencer, and more) is discoverable and callable in-process. Requires UE 5.8+ with the ToolsetRegistry plugin enabled - call ep...
AI agents invoke epic to trigger actions in Ue. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
tool | string | — | Qualified tool name, e.g. 'GASToolsets.AttributeSetToolset.ListAttributeSets' |
input | object | — | call_tool: tool arguments as a JSON object |
action | string | Yes | Action to perform |
toolset | string | — | Qualified toolset name, e.g. 'GASToolsets.AttributeSetToolset' |
inputJson | string | — | call_tool: tool arguments as a raw JSON string (alternative to input) |
nameFilter | string | — | list_toolsets: case-sensitive substring filter on the qualified toolset name |
includeSchemas | boolean | — | list_toolsets: include full per-tool input/output schemas instead of just tool names |
Parameters from the server's own tool schema.
While the visible actions (status, list_toolsets) appear read-only, the description explicitly states this wraps 430+ actions from multiple toolsets (GAS, Niagara, PCG, etc.) that are 'discoverable and callable in-process.' This is an execution gateway to arbitrary engine operations whose effects depend on which toolset actions are invoked.
From the tool's definition The tool provides "first-class actions" for "in-process" execution of Epic's native Unreal 5.8 AI Toolset Registry covering GAS, Niagara, PCG, UMG, StateTree, editor actor/asset/blueprint, sequencer, and more.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Epic's native Unreal 5.8 AI Toolset Registry, wrapped as first-class actions. Every toolset Epic ships (GAS, Niagara, PCG, UMG, StateTree, editor actor/asset/blueprint, sequencer, and more) is discoverable and callable in-process. Requires UE 5.8+ with the ToolsetRegistry plugin enabled - call epic(status) first to check availability. Actions: - status: Report whether Epic's ToolsetRegistry is available and how many toolsets are registered. Never errors (reports available=false with a reason when the plugin is absent). Params: none - list_toolsets: List registered toolsets: name, version, description, tool names + count. Strips the verbose per-tool input/output schemas to stay small - use describe_toolset for those (or includeSchemas). Params: nameFilter? (case-sensitive substring on the qualified name), includeSchemas? (return full tool objects with input/output schemas) - describe_toolset: Full schema for one toolset: every tool with its input/output JSON schema. Params: toolset (qualified name from list_toolsets, e.g. 'GASToolsets.AttributeSetToolset') - call_tool: Execute a registered Epic tool exactly as its MCP server would. Params: toolset (qualified), tool (qualified name from describe_toolset, e.g. 'GASToolsets.AttributeSetToolset.ListAttributeSets'), input? (object) or inputJson? (raw JSON string). Returns the tool's JSON result. Epic 5.8 toolset actions (212): the epic_* actions above wrap Unreal's native ToolsetRegistry tools for this domain. Pass tool arguments via 'input'. It is categorised as a Execute tool in the Ue MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
epic accepts 7 parameters: tool, input, action, toolset, inputJson, nameFilter, includeSchemas. Required: action. The full parameter table on this page comes from the server's own tool schema.
Register the Ue MCP server in PolicyLayer and add a rule for epic: 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.
epic is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the epic 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 epic. 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.
epic 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.
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 →