Unreal Engine MCP Server
This server lets an MCP client drive a running Unreal Editor through one unreal gateway tool with search, describe, execute, and configure operations; the current schema is a placeholder until the editor is reached.
Search 450+ editor capabilities using plain-language queries and receive ready-to-send
nextCallinstructions.Describe a capability’s exact contract, including parameters, schemas, examples, and consent requirements.
Execute validated editor actions such as spawning/managing actors, building levels, Blueprints, UMG UI, materials, lighting, landscapes, foliage, Niagara, PCG, animation, AI, audio, cinematics, networking, and more.
Run Play-In-Editor, synthetic input, screenshots, log reads, profiling, Python, and packaging/build tasks.
Configure which internal tool groups are enabled or disabled without modifying the editor.
Connect locally over native HTTP or a Node.js stdio proxy, protected by a capability token.
Enables AI assistants to control Unreal Engine via Remote Control API, providing tools for asset management, actor spawning and manipulation, level editing, animation and physics control, visual effects creation, sequencer cinematics, and console command execution for game development automation.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Unreal Engine MCP Serverspawn a cube actor at the origin"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
📌 Which version is this? This README describes 0.6.0, the stable release: the plugin on Fab and on the Releases page, and npm
unreal-engine-mcp-server(latest). The previous release, 0.5.30, exposes 23 separate tools instead of one; staying on a 0.5.30 plugin means pinningunreal-engine-mcp-server@0.5.30. See Upgrading from 0.5.x.
Contents · What it does · How it works · Quick start · The unreal tool · Configuration · Security · Engine plugins · Docker · Documentation · Development · Community
What it does
🏗️ Levels and actors Spawn one actor or hundreds in a single call, place and attach them, find the ones sunk into the floor, and load, stream and save levels.
🧩 Blueprints and UI Create Blueprints, variables and components, build whole event graphs in one batch, and lay out UMG widgets, with a preview image to check them.
🎨 Materials and worlds Material graphs and instances, procedural textures, lighting, landscapes, foliage, Niagara effects and PCG graphs.
🕹️ Gameplay Characters and animation, Gameplay Ability System, AI (Behavior Trees, State Trees, EQS), inventory, networking and Enhanced Input.
🎬 Cinematics and audio Level Sequences, cameras, Movie Render Queue and Take Recorder; Sound Cues and MetaSounds.
🧪 Play and verify Run Play-In-Editor with synthetic input, take screenshots the model can see, read logs, profile, run Python, and package builds.
Over 450 capabilities in all, behind a single MCP tool. The assistant finds them by searching in plain words, so nobody has to learn their names. The full list is the generated Action Reference.
Related MCP server: unreal-mcp
How it works
The EngineWire plugin runs inside the editor and does all the work, on the editor's game thread, and serves MCP itself. Clients reach it in one of two ways, and both get the same single tool, unreal:
🌐 Route A · Native HTTP | 🧩 Route B · stdio | |
Path | Client → the plugin's Streamable HTTP server at | Client → |
Node.js | Not needed | 20.19 or later |
Capability token | The client sends it in the | Read from the project, given |
Editor restarts | The client reconnects by hand | The session stays: calls answer |
Best for | Claude Code, Cursor, VS Code, and several clients sharing one editor | Claude Desktop, clients that only launch local commands, and long sessions across editor restarts |
Everything listens on 127.0.0.1 and requires the project's capability token unless you change it.
Quick start
The Quick Start page walks through this with screenshots. You need Unreal Engine 5.0 to 5.8. Installing from Fab needs nothing else; building the plugin from source needs a project with C++ code (a Blueprint-only project can install from Fab or use prebuilt binaries).
1. Add the plugin
From Fab (no compiler needed). Get EngineWire on Fab. In the Epic Games Launcher, open Unreal Engine › Library › Fab Library, find EngineWire and click Install to Engine for your engine version. Open your project, enable EngineWire in Edit › Plugins and restart the editor. The Fab build ships with the native server off: turn on Enable Native MCP Server in Edit › Project Settings › Plugins › EngineWire › Native MCP and restart once more. Fab updates follow Epic's review, so the Fab build can trail the newest release here.
From a release. Download EngineWire-plugin-<version>.zip from the newest release on the Releases page, and copy the EngineWire folder it contains into your project:
MyGame/Plugins/EngineWire/Or use a clone of this repository: copy plugins/EngineWire/, or reference the folder from your .uproject with "AdditionalPluginDirectories": ["C:/Path/To/Unreal_mcp/plugins"].
Open the project and let Unreal rebuild the plugin. When it's loaded, the status bar shows MCP :3000 (0): the plugin serves MCP on port 3000. If you see "Engine modules cannot be compiled at runtime", build the project once in Visual Studio, Rider or Xcode. More in Installation.
https://github.com/user-attachments/assets/d8b86ebc-4364-48c9-9781-de854bf3ef7d
Build the plugin once on a machine with the engine and a compiler, then hand out the zip. No compiler is needed on the target machine:
node scripts/package-plugin.mjs "C:/Program Files/Epic Games/UE_5.7"This writes build/EngineWire-v<version>-UE5.7-<Platform>.zip, where <version> is the package.json version (currently 0.6.0). Unzip it into YourProject/Plugins/. Binaries only work with the engine minor and platform they were built for: a 5.6 build won't load in 5.5, 5.7 or 5.8.
2. Connect your client
Route A · Native HTTP (no Node.js)
Enable Native MCP Server is on by default (Edit › Project Settings › Plugins › EngineWire, port
3000); the Fab build ships with it off. A project where it is off needs it on and an editor restart.Read the capability token the plugin generated:
<YourProject>/Saved/MCP/capability-token. Treat it like a password.Add the server to your client and send the token in the
X-MCP-Capability-Tokenheader. Claude Code:claude mcp add --transport http unreal-engine http://127.0.0.1:3000/mcp --header "X-MCP-Capability-Token: <token>"Or in a project
.mcp.json(Claude Code), reading the token from an environment variable:{ "mcpServers": { "unreal-engine": { "type": "http", "url": "http://127.0.0.1:3000/mcp", "headers": { "X-MCP-Capability-Token": "${UNREAL_MCP_TOKEN}" } } } }Cursor (
.cursor/mcp.json) takes the sameurlandheaderswithouttype. VS Code, Windsurf and others: Connecting Clients.Check it: when the client connects, the count in the status bar goes up.
Route B · stdio (Node.js 20.19+)
The package is a small stdio proxy in front of the same /mcp. A client connected straight to /mcp loses its session whenever the editor closes or crashes, and has to reconnect by hand. Through the proxy, every call answers NOT_CONNECTED while the editor is down, and the first call after it is back reaches it, with no reconnect. It keeps the editor's last tool list, so a session that starts before the editor still gets the real tool.
Add this to your client's MCP configuration, for example Claude Desktop's claude_desktop_config.json:
{
"mcpServers": {
"unreal-engine": {
"command": "npx",
"args": ["-y", "unreal-engine-mcp-server"],
"env": {
"UE_PROJECT_PATH": "C:/Path/To/YourProject"
}
}
}
}Or let the package write it: npx unreal-engine-mcp-server init claude --project C:/Path/To/YourProject shows the entry for Claude Code's .mcp.json (also cursor, vscode, gemini and codex), keeping the file's other servers, and --write saves it. npx unreal-engine-mcp-server doctor checks Node, the token (never shown), the editor's answer and that both sides run the same version.
UE_PROJECT_PATH (the project folder or its .uproject) is how the proxy finds the capability token (MCP_AUTOMATION_CAPABILITY_TOKEN overrides it). UNREAL_MCP_URL points it at another endpoint (default http://127.0.0.1:3000/mcp). Pair it with a 0.6 plugin; a 0.5.x plugin serves its 23 separate tools instead of the unreal gateway.
3. Try it
With the editor open, ask your assistant to "list the actors in the current level", "spawn a point light 300 units above the origin", or "take a screenshot of the viewport". If it doesn't connect, see Troubleshooting.
The unreal tool
Both routes expose exactly one MCP tool, unreal, with four operations. Only the contract the model is about to use gets loaded, instead of hundreds of tool schemas:
Operation | What it does |
| Finds capabilities from 2-4 plain words, such as |
| Returns one capability's exact contract: parameters, schemas, an example, and the consent grant when one is needed |
| Runs one capability with validated parameters and returns the data plus a receipt of what changed |
| Enables or disables groups of internal tools; never touches the editor |
A typical exchange:
{ "operation": "search", "query": "spawn actor" }{ "operation": "describe", "tool": "control_actor", "action": "spawn" }{
"operation": "execute",
"tool": "control_actor",
"action": "spawn",
"params": { "classPath": "/Script/Engine.PointLight", "actorName": "KeyLight", "location": [0, 0, 300] }
}Parameters are strict. An undeclared name is refused with
UNDECLARED_PARAMETERand the list of allowed names; every error carries an executablenextCall.Deletes need consent. Every destructive capability, plus some risky writes, only runs with the
consentGrantfromdescribe, passed back as a top-levelconsentfield.Names. A call names the
tool+actionpair or a capability id, such as"capability": "control_actor.spawn".
Full reference with real replies: Using the Gateway.
Migrating from direct tool calls
The single unreal tool is permanent on both routes; there is no opt-out and no 23-tool listing to restore. A client that still calls a canonical tool name directly (tools/call with name: "manage_asset", name: "control_actor", …) receives a bounded, copy-paste-executable DIRECT_TOOL_CALL_REMOVED receipt instead of a routed call. Its nextCall drills exactly one level: { "operation": "search" } for an unknown name, { "operation": "describe", "tool": "<tool>" } when no action was given, or { "operation": "execute", "tool": "<tool>", "action": "<action>", "params": { ... } } when the call already named an action. Run that nextCall through unreal to finish the migration. See Upgrading.
Protocol versions
Both routes negotiate the MCP protocol version at initialize: 2025-11-25 (latest), 2025-06-18 or 2025-03-26. A client asking for an older version is answered with 2025-11-25. An unsupported MCP-Protocol-Version header on the native route gets HTTP 400. Both also serve MCP 2026-07-28 per request, with no initialize or session, and answer server/discover with it. Details: docs/protocol.md.
These route requests inside the gateway; clients never list them. More in the Tools Reference.
Category | Tool | Covers |
Core |
| Assets and folders, materials and material graphs, textures and render targets, data tables, structs, enums, source control |
Core |
| Blueprints, components, variables, event graphs, UMG widgets, layout, bindings, widget animations |
Core |
| Spawning, transforms, attachment, components, materials, tags, placement audits |
Core |
| Play-In-Editor, synthetic input, screenshots, viewport camera, undo, editor preferences |
Core |
| Create, load, save, stream, import and export levels; world settings; lighting builds |
Core |
| Console commands, logs, project settings, profiling, builds and packaging, tests, Python |
Core |
| Read and write any UObject's properties, components and class info |
Core |
| Which internal tools are enabled (through |
World |
| Landscapes, foliage, lights and sky, water, weather, splines, procedural terrain |
World |
| Sublevels, World Partition, streaming, data layers, HLOD, volumes |
World |
| Geometry Script meshes: booleans, deformers, UVs, collision, LODs, polygon cages, subdivision surfaces, material ids, vertex-color masks |
World |
| PCG graphs: create, add and connect nodes, execute |
Gameplay |
| Animation Blueprints, blend spaces, montages, skeletons, Control Rig and IK, ragdolls, cloth, vehicles |
Gameplay |
| Character Blueprints, movement, MetaHuman |
Gameplay |
| Weapons, projectiles, hit detection |
Gameplay |
| Niagara systems, emitters and modules, debug shapes |
Gameplay |
| Gameplay Ability System: abilities, attributes, effects |
Gameplay |
| AI controllers, Behavior Trees, EQS, State Trees, Smart Objects, perception, navigation |
Gameplay |
| Items, loot tables, crafting recipes |
Gameplay |
| Doors and other interactables |
Utility |
| Sounds, audio components, Sound Cues, MetaSounds, attenuation, mixes |
Utility |
| Level Sequences, Movie Render Queue, media, Take Recorder, replays |
Utility |
| Replication, RPCs, sessions, game framework classes, Enhanced Input |
Configuration
Most setups touch one setting: UE_PROJECT_PATH for Route B; Route A needs none. Everything is listed on the Configuration page.
Plugin settings (Project Settings › Plugins › EngineWire, saved in Config/DefaultGame.ini):
Setting | Default | |
Enable Native MCP Server | on | Serve MCP over HTTP at |
Native MCP Port |
| The |
Listen Ports |
| The plugin's WebSocket listener; neither route uses it |
Require Capability Token | on | Both routes refuse clients without the token |
Allow Non Loopback | off | LAN access for both listeners. See Security. |
Environment variables (Route B only, in the client's env block):
Variable | Default | |
| unset | Project folder or |
| read from the token file | Token to present, when the proxy can't read the project folder |
|
| The editor's |
|
|
|
Security
Local by default. Both routes listen on
127.0.0.1only. The native server never binds off-loopback: it has no TLS, so reach it from another machine through an SSH tunnel (ssh -L 3000:127.0.0.1:3000) or a TLS proxy. The WebSocket bridge binds a LAN address only with Allow Non Loopback, Require Capability Token and Enable Tls all on. The proxy sends the token to another machine only withUNREAL_MCP_ALLOW_REMOTE_TOKEN=1.Capability token. Generated per project at
<Project>/Saved/MCP/capability-token(a value typed into Capability Token overrides it) and compared in constant time. Delete the file and restart the editor to rotate it.Consent for destructive work. Deletes and some other writes need a per-call consent grant, which the plugin checks itself.
Guard rails. Asset paths are limited to
/Game,/Engine,/Script,/Tempand/Niagara, and a content path may also sit under a mount the connected editor reports; arguments the server treats as files (such asfilePath, andoutputPatheven where it names an asset) never use the reported mounts; console commands that chain or quit the editor are blocked; the plugin's own settings are out of reach of automation.
Details: Security. Please report vulnerabilities privately through GitHub security advisories.
Engine plugins
The bridge declares its engine-plugin dependencies, so Unreal enables them together with it.
Plugin | Used for |
Python Editor Script Plugin | Python-backed editor automation, |
Editor Scripting Utilities | Asset and actor subsystem operations |
Niagara | Visual effects |
Gameplay Abilities |
|
Smart Objects | AI smart objects |
Plugin | Used for |
Level Sequence Editor, Takes, Movie Render Pipeline, Movie Pipeline Mask Render Pass, Electra Player |
|
Control Rig, RigVM, IK Rig, Animation Data |
|
Chaos Vehicles, Chaos Cloth |
|
Niagara Editor |
|
Behavior Tree Editor, Environment Query Editor, StateTree, Mass Gameplay |
|
Geometry Scripting, Geometry Processing, Mesh Modeling Toolset, Procedural Mesh Component |
|
PCG |
|
Game Features |
|
Data Registry |
|
MetaSound, Synthesis |
|
Enhanced Input, Online Subsystem, Online Subsystem Utils |
|
Interchange, Interchange OpenUSD, Data Validation, StructUtils | Import/export, validation, struct helpers |
Fab, Bridge | Fab asset library access (optional |
The plugin targets every Unreal Engine minor from 5.0 to 5.8. If it fails to build on yours, please open an issue with the build log.
Docker
The image runs the stdio proxy. It has to reach the editor's /mcp on 127.0.0.1:3000, so use host networking (Linux), and pass the token because the container can't read your project folder:
docker build -t unreal-mcp .
docker run -i --rm --network host -e MCP_AUTOMATION_CAPABILITY_TOKEN=<token> unreal-mcpUse -i without -t: a TTY corrupts the MCP stream on stdout.
Documentation
📖 Wiki | Quick Start, Installation, Connecting Clients, Using the Gateway, Configuration, Security, Troubleshooting, FAQ, Upgrading |
Every capability with its effect, scope and consent, generated from the capability records | |
The gateway contract, with the source file behind each claim | |
📡 Protocol | Transports, version negotiation, cancellation |
Scopes, consent, path gating, idempotency, refusal codes | |
Test suites and how to add cases | |
Adding an editor action: record, handler, route and tests, plus the rules for plugin code | |
🗺️ Roadmap | Development roadmap |
What changed in each release |
Development
npm install
npm run build # clean + compile TypeScript to dist/
npm run dev # run from source with ts-node
npm run lint # ESLint (CI fails on any warning)
npm run type-check # tsc --noEmit, sources and tests
npm run test:unit # Vitest unit tests (no Unreal required)
npm run test:params # strict parameter audit
npm run registry:generate # capability records -> generated contracts, native shards, action reference
npm run registry:check # fail if generated artifacts drift
npm run manifest:check # fail if the gateway manifest drifts
npm run eval:check # search-ranking corpus
npm run version:check # all version sources agree
npm test # integration suite (needs a live Unreal Editor serving /mcp)The capability records in src/tools/catalog/capabilities/records/ are the single source of truth; every *.generated.* file, the plugin's MCP/Generated/ shards and the action reference are generated from them. Never hand-edit generated files. How to add a capability: Development.
CI runs, in order: ESLint (npx eslint . --max-warnings=0), type-check, unit tests, registry:check, manifest:check, headers:check, the strict parameter audit (test:params) and eval:check, then a blocking runtime dependency audit (npm audit --omit=dev --audit-level=moderate) and an informational full-tree audit. A Node 20.19 / 26 matrix adds build. Plugin packaging runs only when an Unreal Engine root is configured, because CI runners don't ship an engine. Release archives exclude Binaries/, Intermediate/ and Saved/.
Community
Questions, ideas, show and tell | |
🐞 Issues | Bug reports and feature requests |
Roadmap progress and priorities |
Contributing: keep pull requests small and focused, with a Conventional Commits title; include reproduction steps for bugs; follow the existing code style. See CONTRIBUTING.md.
License
MIT. See LICENSE.
Available Tools
1 toolunrealDInspect
Unreal Engine editor: operation search, describe, execute or configure. The editor has not been reached yet, so this is a placeholder; the full contract replaces it once the editor answers.
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure, and it discloses nothing: no mention of whether 'execute' mutates editor state, what permissions are needed, or how the editor is reached. It explicitly states the editor has not been reached, so even basic operational behavior is unknown.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
It is short and front-loads the domain and operation list, which is good structure. The second sentence, however, is an admission of incompleteness rather than content, so the text is more under-specified than genuinely concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, the description should explain what search/describe/execute/configure actually do and what comes back; instead it openly says the contract is pending. An agent cannot confidently invoke this tool from this definition.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There is only one parameter ('operation') and its enum values are already fully visible in the schema; the description merely restates those four values without explaining what any of them means or returns. Zero schema description coverage is not compensated by the text.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a domain (Unreal Engine editor) and four operation verbs (search, describe, execute, configure), but it does not say what those operations act on or return. It then declares itself a placeholder, which by design leaves the actual purpose undefined for the agent reading it.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to pick one operation over another, no prerequisites, and no indication of what each mode does. An agent seeing 'search' vs 'describe' vs 'execute' gets no basis for choosing, and the placeholder caveat gives none either.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v0.6.0- Changed
unreal17 fields changed- removed
Input schema / additionalPropertiesRemoved value: -false - removed
Input schema / properties / actionRemoved value: -{ - "description": "Exact action name returned by describe. For configure, this is a manage_tools action.", - "type": "string" -} - removed
Input schema / properties / capabilityRemoved value: -{ - "description": "Exact canonical capability ID (or declared alias) returned by search, e.g. asset.import. Preferred selector for describe.", - "type": "string" -} - removed
Input schema / properties / consentRemoved value: -{ - "additionalProperties": false, - "description": "Per-call consent grant for a capability whose policy.consent is not 'none'. Bound to one capability and one call; never persisted, inherited or reused. Read the exact grant from describe.consentGrant. Use with execute only.", - "properties": { - "acknowledge": { - "description": "Acknowledgement strength. 'explicit' satisfies an explicit policy; 'elevated' is required by a destructive policy and also satisfies explicit.", - "enum": [ - "explicit", - "elevated" - ], - "type": "string" - }, - "capability": { - "description": "Exact canonical capability ID this grant authorizes, as returned by describe.", - "type": "string" - } - }, - "required": [ - "capability", - "acknowledge" - ], - "type": "object" -} - removed
Input schema / properties / cursorRemoved value: -{ - "description": "Opaque search cursor from a previous response nextCursor. Supersedes offset.", - "type": "string" -} - removed
Input schema / properties / domainRemoved value: -{ - "description": "Capability domain to browse or filter by. Call describe with no selector to list domains.", - "type": "string" -} - removed
Input schema / properties / effectRemoved value: -{ - "description": "Filter search results by declared behavior effect.", - "enum": [ - "read", - "write", - "destructive" - ], - "type": "string" -} - removed
Input schema / properties / familyRemoved value: -{ - "description": "Capability family inside a domain. Call describe with a domain to list its families.", - "type": "string" -} - removed
Input schema / properties / limitRemoved value: -{ - "description": "Maximum search results to return. Defaults to 12.", - "maximum": 25, - "minimum": 1, - "type": "integer" -} - removed
Input schema / properties / maxBytesRemoved value: -{ - "description": "Serialized byte ceiling for a search response. Results are dropped from the end until the response fits.", - "maximum": 262144, - "minimum": 512, - "type": "integer" -} - removed
Input schema / properties / offsetRemoved value: -{ - "description": "Zero-based search result offset. Defaults to 0.", - "minimum": 0, - "type": "integer" -} - removed
Input schema / properties / operation / descriptionRemoved value: -"search finds capabilities. describe returns an exact parent-tool contract. execute runs one validated action. configure manages internal capability availability." - removed
Input schema / properties / paramRemoved value: -{ - "description": "Exact parameter name (tool-union catalog) to inspect. Requires tool and action for full drill-down; resolves the single parameter schema. Use with describe only.", - "type": "string" -} - removed
Input schema / properties / paramsRemoved value: -{ - "additionalProperties": true, - "description": "Parameters for execute or configure. Keys are the action-specific parameter names returned by describe. Never include action or subAction here.", - "type": "object" -} - removed
Input schema / properties / queryRemoved value: -{ - "description": "Search words for tools, categories, descriptions, or actions.", - "type": "string" -} - removed
Input schema / properties / toolRemoved value: -{ - "description": "Exact canonical parent tool name returned by search or describe.", - "type": "string" -} - changed
Output schema / (root)Previous value: -{ - "additionalProperties": true, - "properties": { - "action": { - "type": "string" - }, - "actionCount": { - "type": "integer" - }, - "actionHasMore": { - "type": "boolean" - }, - "actionLimit": { - "type": "integer" - }, - "actionOffset": { - "type": "integer" - }, - "actions": { - "description": "Paginated/filterable action list on tool-only describe.", - "type": "array" - }, - "availability": { - "description": "Whether the capability is available, disabled or unavailable, and why." - }, - "availableActions": { - "type": "array" - }, - "availableParameters": { - "type": "array" - }, - "behavior": { - "type": "object" - }, - "capabilities": { - "description": "Bounded capability list on a family-level describe.", - "type": "array" - }, - "capability": { - "description": "Canonical capability ID this response describes.", - "type": "string" - }, - "catalogRevision": { - "description": "Revision of the generated canonical capability catalog this response was served from.", - "type": "string" - }, - "consentGrant": { - "description": "Exact consent grant this capability requires, ready to pass back as the execute call's consent sibling. Absent when policy.consent is 'none'.", - "type": "object" - }, - "cost": { - "type": "object" - }, - "data": { - "description": "Execute payload projected against the capability's declared output schema. Same value as receipt.data, and the same location the native /mcp surface publishes." - }, - "deprecation": { - "type": "object" - }, - "domain": { - "type": "string" - }, - "domains": { - "description": "Bounded domain list on a catalog-level describe.", - "type": "array" - }, - "drillDown": { - "description": "Example nextCall payload to drill one level deeper.", - "type": "object" - }, - "error": { - "type": "string" - }, - "errorCode": { - "type": "string" - }, - "families": { - "description": "Bounded family list on a domain-level describe.", - "type": "array" - }, - "family": { - "type": "string" - }, - "filters": { - "description": "Filters applied to this search.", - "type": "object" - }, - "hasMore": { - "type": "boolean" - }, - "hashes": { - "description": "Per-record schema and content hashes from the generated catalog.", - "type": "object" - }, - "inputSchema": { - "description": "Exact input schema of the described capability. Never a parent-tool union.", - "type": "object" - }, - "limit": { - "type": "integer" - }, - "maxBytes": { - "type": "integer" - }, - "message": { - "type": "string" - }, - "migratedFrom": { - "description": "Legacy tool/action pair that resolved to this capability.", - "type": "object" - }, - "nextCall": { - "description": "Directly-invokable gateway request for guided self-correction.", - "type": "object" - }, - "nextCursor": { - "description": "Cursor to pass back as cursor to continue a search.", - "type": "string" - }, - "offset": { - "type": "integer" - }, - "operation": { - "type": "string" - }, - "outputSchema": { - "description": "Exact output schema of the described capability.", - "type": "object" - }, - "outputs": { - "type": "array" - }, - "param": { - "type": "string" - }, - "parameterCount": { - "type": "integer" - }, - "parameterHasMore": { - "type": "boolean" - }, - "parameterLimit": { - "type": "integer" - }, - "parameterOffset": { - "type": "integer" - }, - "parameters": { - "description": "Paginated/filterable compact parameter catalog on tool+action describe.", - "type": "array" - }, - "parentTool": { - "description": "Legacy parent tool that dispatches the described capability.", - "type": "string" - }, - "perActionSchemas": { - "type": "boolean" - }, - "policy": { - "type": "object" - }, - "reasons": { - "type": "array" - }, - "required": { - "description": "Whether the described param is required.", - "type": "boolean" - }, - "resolvedFromAlias": { - "description": "Declared alias that resolved to this capability.", - "type": "string" - }, - "result": {}, - "results": { - "type": "array" - }, - "runnable": { - "description": "False when the capability cannot currently be executed; nextCall then points at the fix.", - "type": "boolean" - }, - "schema": { - "description": "Full schema of the single described param.", - "type": "object" - }, - "scope": { - "description": "Catalog scope: 'tool' for a tool summary, 'union' for the tool-union parameter catalog.", - "type": "string" - }, - "success": { - "type": "boolean" - }, - "suggestions": { - "description": "Closest-match names for an invalid tool/action/param call.", - "type": "array" - }, - "tool": { - "type": "string" - }, - "total": { - "type": "integer" - }, - "truncated": { - "description": "True when results were dropped to fit the byte budget.", - "type": "boolean" - } - }, - "required": [ - "success", - "operation" - ], - "type": "object" -}New value: +null
1 tool update
v0.5.30- First observed
unreal
TDQS
Scored across 1 tool
With only one tool there is no cross-tool ambiguity for an agent to resolve, which is a plus. However, that single tool multiplexes search, describe, execute, and configure operations behind an operation parameter, so the real ambiguity is pushed inside the tool rather than eliminated.
The lone name 'unreal' is a plain lowercase noun with no verb_noun convention, so there is no pattern for an agent to learn or rely on. It is not inconsistent with anything, but it establishes no predictable convention for the eventual expanded surface.
One placeholder tool is far too thin for something as broad as driving an Unreal Engine editor, and it forces every capability through a single generic entry point. The count is a deliberate stub, but as a shipped surface it is severely under-scoped.
The description explicitly states the editor has not been reached and the contract is a placeholder, so there is no real CRUD or lifecycle coverage to assess. Agents cannot depend on any concrete operation until the editor responds and replaces the tool.
Maintenance
Related MCP Connectors
Make games with AI: one MCP server that connects your agent to Unity, Unreal and Godot editors.
Turn prompts into production-ready game assets: animated characters, textures, terrain, VFX, HUD.
- DNS-DATA RemoteDeprecatedcom.dns-data
Connect AI assistants to authorized Windows and macOS devices for files, commands, and management.
AI film studio: your stories, shots and edits, plus Unreal and Unity orders, from your account.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to control and automate Unreal Engine through a native C++ Automation Bridge plugin. It supports a comprehensive range of tasks including asset management, actor manipulation, editor control, and blueprint graph editing.1,312 npm1MIT
- AlicenseCqualityDmaintenanceEnables natural language interaction with Unreal Engine, providing 127 tools across 16 subsystems for tasks like actor manipulation, asset management, blueprint creation, and more, using built-in Python and Remote Control plugins.1008MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to interact with Unreal Engine via Remote Control API for actor, asset, level, and editor operations.2213 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to control Unreal Engine through a native C++ Automation Bridge plugin, supporting asset management, actor control, sequencer, and more via HTTP or WebSocket transport.1,163 npmMIT