Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

io.github.ChiR24/unreal-engine-mcp

NPM · UNREAL-ENGINE-MCP-SERVER · SCANNED AUG 3

MCP server for Unreal Engine 5 with 23 tools for game development automation.

+16 this week 57 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security87
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (97 of 101), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (97 of 101), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency19
Schema Quality & AI Usability46
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (poor).Fail
  • Context-footprint check failed: tool/resource definitions use about 24790 tokens (~854/item across 29 items; 23 tools + 6 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage87
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 60% of tool parameters carry a description.Partial
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · unreal-engine-mcp-server

# add to Claude Code
claude mcp add chir24-unreal-engine-mcp -- npx -y unreal-engine-mcp-server
# add to Codex CLI
codex mcp add chir24-unreal-engine-mcp -- npx -y unreal-engine-mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "chir24-unreal-engine-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "unreal-engine-mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add chir24-unreal-engine-mcp --command npx --arg -y --arg unreal-engine-mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  chir24-unreal-engine-mcp:
    command: "npx"
    args: ["-y", "unreal-engine-mcp-server"]
// mcp.json
{
  "mcpServers": {
    "chir24-unreal-engine-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "unreal-engine-mcp-server"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 3 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 2 Aug 26 +39
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • Schema quality: 100 → unverified functional
    • Tool coverage: 100 → unverified functional
    • License: unverified → pass functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
    • Stability: unverified → 0.23 functional
    • Schema quality: unverified → poor functional
    • Licence: MIT functional
  • 31 Jul 26 −24
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 +23
    • Tool coverage: unverified → 100 functional
    • Schema quality: unverified → 100 functional
  • 28 Jul 26 −23
    • Schema quality: 100 → unverified functional
    • Tool coverage: 100 → unverified functional
  • 27 Jul 26 41

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 97 packages

97 packages in the resolved dependency tree · 96 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 23 exposed · ~24,727 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
manage_pcg ~672

Create, edit, execute, and configure PCG graphs: graph assets, input/sampler/filter/spawner nodes, pin connections, node settings, and partition grid size. Required: action. Select one enum value, then provide only parameters relevant to that action. Params by action: graphPath, parentGraphPath, subgraphPath, assetPath, path, name, nodeType, settingsClass, nodeId, nodeName, title, sourceNodeId, targetNodeId, sourcePin, targetPin, inputName, outputName, actorName, componentName, componentPath, classPath, actorClass, meshPath, texturePath, createComponent, force, wait, gridSize, scope, settings, x, y, posX, posY, save, overwrite, timeoutMs, params.

NameTypeReqDescription
actionstringyesPCG graph action to perform
actorClassstring
actorNamestringName of the actor.
assetPathstringAsset path (e.g., /Game/Path/Asset).
classPathstring
componentNamestringName of the component.
componentPathstringComponent path/name for PCG execution.
createComponentboolean
forceboolean
graphPathstringPCG graph asset path (e.g., /Game/PCG/PCG_MyGraph).
gridSizenumber
inputNamestringName of the pin.
meshPathstringMesh asset path.
namestringName identifier.
nodeIdstringID of the node.
nodeNamestringName of the node.
nodeTypestringPCG node type alias or UPCGSettings class path/name.
outputNamestringName of the pin.
overwritebooleanOverwrite if the asset/file already exists.
paramsobjectOptional action-specific parameters. These are merged with top-level arguments before routing for clients that cannot send arbitrary top-level fields.
parentGraphPathstringParent PCG graph asset path for subgraph insertion.
pathstringPath to a directory.
posXnumber
posYnumber
savebooleanSave the asset(s) after the operation.
scopestringPartition grid target scope.
settingsobjectNode settings keyed by reflected PCG settings property name.
settingsClassstringUPCGSettings class path/name for the PCG node.
sourceNodeIdstringID of the source node.
sourcePinstringName of the source pin.
subgraphPathstringPCG subgraph asset path used by subgraph nodes.
targetNodeIdstringID of the target node.
targetPinstringName of the target pin.
texturePathstringTexture asset path.
timeoutMsnumber
titlestring
waitboolean
xnumber
ynumber

No output schema declared.

No examples provided.

manage_sequence ~420

Edit Level Sequences: add tracks, bind actors, set keyframes, control playback, and record camera. Required: action. Select one enum value, then provide only parameters relevant to that action. Params by action: name, path, actorName, actorNames, frame, value, property, destinationPath, newName, speed, startTime, loopMode, className, spawnable, trackType, trackName, muted, solo, locked, startFrame, endFrame, frameRate, resolution, start, end, lengthInFrames, playbackStart, playbackEnd, metadata, params.

NameTypeReqDescription
actionstringyesAction
actorNamestringName of the actor.
actorNamesarray
classNamestring
destinationPathstringDestination path for move/copy.
endnumber
endFramenumber
framenumber
frameRatestring
lengthInFramesnumber
lockedboolean
loopModestring
metadataobject
mutedboolean
namestringName identifier.
newNamestringNew name for renaming.
paramsobjectOptional action-specific parameters. These are merged with top-level arguments before routing for clients that cannot send arbitrary top-level fields.
pathstringAsset path (e.g., /Game/Path/Asset).
playbackEndnumber
playbackStartnumber
propertystringName of the property.
resolutionstring
soloboolean
spawnableboolean
speednumber
startnumber
startFramenumber
startTimenumber
trackNamestring
trackTypestring
valueobject

No output schema declared.

No examples provided.

manage_tools ~175

Dynamic MCP tool management. List canonical tools, view category counts, and enable/disable tools or categories at runtime. Required: action. Select one enum value, then provide only parameters relevant to that action. Params by action: tools, category, params.

NameTypeReqDescription
actionstringyeslist_tools: show canonical tools with status. list_categories: show category counts. enable/disable_tools: toggle specific tools. enable/disable_category: toggle category. get_status: current state.…
categorystringCategory name to enable/disable (core, world, gameplay, utility, all)
paramsobjectOptional action-specific parameters. These are merged with top-level arguments before routing for clients that cannot send arbitrary top-level fields.
toolsarrayTool names to enable/disable

No output schema declared.

No examples provided.

system_control ~811

Control the project runtime: profiling, benchmarks, scalability/LOD/Nanite settings, CVars, console commands, Python scripts, UBT, tests, logs, and widgets. Required: action. Select one enum value, then provide only parameters relevant to that action. Params by action: profileType, category, level, enabled, resolution, command, target, platform, configuration, arguments, filter, channels, widgetPath, childClass, parentName, section, key, value, code, file, mode, returnBase64, includeMetadata, metadata, type, duration, outputPath, detailed, scale, maxFPS, poolSize, boostPlayerLocation, forceLOD, lodBias, enableInstancing, enableBatching, mergeActors, actors, streamingDistance, cellSize, categoryName, filename, height, message, name, packageName, assetPath, path, paths, recursive, replaceSourceActors, savePath, text, volume, widgetId, width, windowed, params.

NameTypeReqDescription
actionstringyesAction
actorsarray
argumentsstring
assetPathstringAsset path (e.g., /Game/Path/Asset).
boostPlayerLocationboolean
categorystring
categoryNamestring
cellSizenumber
channelsstring
childClassstring
codestringPython code to execute inline
commandstring
configurationstring
detailedboolean
durationnumber
enableBatchingboolean
enableInstancingboolean
enabledbooleanWhether the item/feature is enabled.
filestringPath to .py file to execute
filenamestring
filterstring
forceLODnumber
heightnumber
includeMetadataboolean
keystring
levelnumber
lodBiasnumber
maxFPSnumber
mergeActorsboolean
messagestring
metadataobject
modestringScreenshot source. editor_viewport captures the active editor viewport; game_viewport captures the PIE/game viewport; full_editor_window captures the full Slate editor window and returns imageBase64…
namestringName identifier.
outputPathstringOutput file or directory path.
packageNamestring
paramsobjectOptional action-specific parameters. These are merged with top-level arguments before routing for clients that cannot send arbitrary top-level fields.
parentNamestring
pathstringAsset path (e.g., /Game/Path/Asset).
pathsarray
platformstring
poolSizenumber
profileTypestring
recursivebooleanPerform the operation recursively.
replaceSourceActorsboolean
resolutionstringResolution setting (e.g., 1024x1024).
returnBase64booleanReturn PNG image data as base64 when supported. Defaults to true for full_editor_window and game_viewport screenshot modes.
savePathstringPath to save the asset.
scalenumber
sectionstring
streamingDistancenumber
targetstring
textstring
typestring
valuestring
volumenumber
widgetIdstring
widgetPathstringWidget blueprint path.
widthnumber
windowedboolean

No output schema declared.

No examples provided.