Skip to main content
Glama
unreal-lazy-mcp

unreal-lazy-mcp

by abc11010xyz

unreal-lazy-mcp

Put it in front of Unreal Engine 5.8's built-in MCP server: about half the tokens, and almost no failed tool calls. The official server is not replaced or modified; your agent searches its 832 editor tools instead of guessing names.

Same 18 tasks, Claude Code + Sonnet 5.5

Official server

With unreal-lazy-mcp

Failed tool calls

39

0

Tokens

7.98 M

3.56 M (-55%)

Cost reported by Claude Code

$5.17

$1.95

The same work cost about 38% as much - roughly 2.5x more tasks for the same spend. With Haiku 5.5: failed calls 64 -> 1, tokens -38%. Non-English requests work too: the same six tasks in Korean (Haiku 5.5) - failed calls 68 -> 1, tokens -50%.

Before and after

From the benchmark logs (task B06: create a material, wire a constant to Metallic, save it).

Official server - the agent guesses a name:

call_tool(AssetTools, "save_asset")        -> Unknown tool save_asset

With the wrapper - the agent searches first:

find_tools("save asset")                   -> 1. AssetTools.save_assets  "Saves assets to disk."
invoke(AssetTools, "save_assets", {...})   -> true

A guessed name still gets a pointer: get_tool_details(AssetTools, "save_asset") returns found: false with save_assets as the first suggestion.

Related MCP server: ue5-automation

Quick start

You need Unreal Engine 5.8 (5.9 is not supported yet) and uv.

  1. In the editor, enable the Unreal MCP and All Toolsets plugins (Edit > Plugins) and start the MCP server: turn on Auto Start Server under Editor Preferences > Model Context Protocol, or launch the editor with -ModelContextProtocolStartServer. Leave Enable Tool Search on (the default).

  2. Add the wrapper to your MCP client. Most clients use this format:

    {
      "mcpServers": {
        "unreal-lazy": {
          "command": "uvx",
          "args": ["--from", "git+https://github.com/abc11010xyz/unreal-lazy-mcp", "unreal-lazy-mcp"]
        }
      }
    }

    Claude Code, in one command:

    claude mcp add unreal-lazy -- uvx --from git+https://github.com/abc11010xyz/unreal-lazy-mcp unreal-lazy-mcp

    Run it in your Unreal project folder (it registers the server for that folder), or add --scope user to use it everywhere. Or as a plugin: claude plugin marketplace add abc11010xyz/unreal-lazy-mcp, then claude plugin install unreal-lazy-mcp@unreal-lazy-mcp. Other clients (VS Code, Codex, Cursor, Claude Desktop), offline use and troubleshooting: configuration.

    Do not also register the editor's own unreal-mcp entry (the one Generate Client Config writes into your project folder, such as .mcp.json) or Epic's unreal-mcp-proxy: the agent could then call the official server directly and skip both the search and the delete confirmation.

  3. Ask for something in the editor. The first tool call reads the editor's tool list once (about 20 seconds); there is nothing else to set up.

Deleting assets or actors and switching levels ask you first; everything else runs without asking. The confirmation needs a client that supports MCP elicitation (Claude Code does); elsewhere those calls are refused. The numbers above were measured with Claude Code; other clients work the same way but were not measured. Settings, install without uv, removal: configuration.

More

Unofficial; not affiliated with Epic Games. MIT license.

Available Tools

4 tools
find_toolsA

Find Unreal Engine tool candidates for the NEXT action in a user's task, not necessarily the whole task. In query, describe the specific action using the user's actual intent; preserve quoted text, proper nouns, asset names and /Game/... paths exactly. Pass short English action/object keywords in english_keywords when useful for non-English text. Search again only for a different step/capability; never retry an identical query just to fish for an answer. Blueprint graph logic: BlueprintTools.write_graph_dsl writes and compiles a whole graph in one call (read get_graph_dsl_docs first) - usually fewer calls than adding nodes and pins one by one.

Inputs: query (required), k, english_keywords. Returns: result

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.

Inputs: tool (required), toolset (required). Returns: result

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.

Inputs: tool (required), toolset (required), arguments.

list_toolsetsA

List Unreal toolsets (id and tool count). With query, return only related toolsets. find_tools is usually more direct.

Inputs: query. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 4 tools

    Disambiguation4/5

    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.

    Naming Consistency4/5

    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.

    Tool Count4/5

    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.

    Completeness4/5

    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.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to operate the Unreal Editor via MCP: reading, creating, and editing blueprints at the node level, authoring materials and UMG widgets, auditing projects, and verifying runtime behavior in PIE with read-back checks.
      34
      1
      Apache 2.0
    • A
      license
      B
      quality
      B
      maintenance
      Enables Unreal Engine editor development through typed Jev decisions and guarded MCP tools, including tool recommendation, diagnostic classification, scene inspection, and preview/apply blockout operations with undo.
      54
      MIT
    • F
      license
      Not graded
      quality
      B
      maintenance
      Enables AI coding agents to inspect and work with Unreal Engine projects by parsing C++ symbols, Blueprints, and .uasset data over MCP, supporting tasks like symbol tracing, asset search, and code generation.
      -