unreal-lazy-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Lazy discovery for Unreal Engine tools. For a multi-step user task, resolve each distinct capability in sequence (for example locate an asset, inspect dependencies, then inspect referencers). For each new capability use find_tools, inspect the chosen tool with get_tool_details, and invoke with verified arguments. Use exact paths, native node type names, pin labels, and identifiers returned by Unreal discovery and schema calls rather than guessing aliases. Graph input/output terminals are not creatable native node types: inspect graph structure, query schemas only for listed node types, connect actual pins, and remove unrelated input sources. For object properties use the exact creation refPath and inspect available names/types before requesting values. Reuse schemas you already inspected instead of searching again. Once the actual Unreal response confirms the requested result, stop exploratory searching and report it. Do not repeat identical searches or call tools without checking schemas. Report tool failures faithfully.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_toolsetsA | List Unreal toolsets (id and tool count). With |
| find_toolsA | Find Unreal Engine tool candidates for the NEXT action in a user's task, not necessarily the whole task. In |
| get_tool_detailsB | Return the input schema for a tool. Inspect it before invoke; for a different action use find_tools again if its tool is not yet known. Preserve actual UE refPaths. |
| invokeB | Run the selected Unreal tool. Only tools on the configured execution allowlist run (not necessarily read-only). A successful call returns the Native MCP result blocks and structuredContent unchanged; inspect its isError for Native tool failures. Wrapper denials and transport errors return Wrapper status JSON. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
The four tools occupy distinct roles: discovery (find_tools), browsing (list_toolsets), schema inspection (get_tool_details), and execution (invoke). The only overlap is between find_tools and list_toolsets, but the descriptions explicitly steer users toward find_tools, keeping boundaries clear.
Three of four tools follow a clean verb_noun pattern (get_tool_details, list_toolsets, find_tools). The bare verb 'invoke' is a minor but understandable deviation for the terminal execution step.
Four tools is a lean but well-scoped gateway pattern where each tool earns its place (discover, browse, inspect, execute). It is slightly on the minimal side but not thin given the proxy role.
The surface covers the full discovery-to-execution lifecycle for a proxied toolset, including schema inspection before invocation. Minor gaps exist (no bulk tool listing within a toolset, no batch invoke), but agents can work around them via find_tools and repeated invoke calls.