Unreal Engine MCP Server
The Unreal Engine MCP Server allows AI assistants to control and automate Unreal Engine projects through a unified unreal gateway tool. It provides search, description, execution, and runtime configuration of a wide range of capabilities, covering nearly every aspect of game development.
Gateway Operations:
search — discover tools by keyword, category, or action name, with suggestions for invalid queries.
describe — retrieve exact contracts (actions, parameters, schemas) for a given tool or capability.
execute — run validated actions with consent handling for sensitive operations.
configure — enable or disable internal capabilities at runtime.
Core Capabilities:
Asset Management: browse, import, duplicate, rename, delete assets; create and edit materials, blueprints, render targets, behavior trees, UMG widgets, and user-defined structs.
Actor & Level Control: spawn, delete, transform, apply physics, manage tags and components; load/save levels, manage sublevels, World Partition, data layers, HLOD, volumes, lighting, and streaming.
Editor Control: manage Play‑In‑Editor (PIE) sessions, camera, viewport, take screenshots, set bookmarks.
Blueprints & Graphs: edit Blueprint, Niagara, Material, and Behavior Tree graphs; manipulate SCS components, UMG layout, bindings, and animations.
Animation & Physics: animate with Blueprints, state machines, skeletons, sockets; set up cloth, vehicles, ragdolls, Control Rig, and IK.
Visual Effects: create and control Niagara particles, GPU simulations, procedural effects, and debug shapes.
Audio: manage sound cues, audio components, sound mixes, MetaSounds, and ambient sounds.
Sequencer & Cinematics: control timelines, Movie Render Queue, media playback, Take Recorder, and replay systems.
World Building: sculpt landscapes, place foliage, generate procedural terrain and spline-based elements (roads, rivers, fences); create procedural geometry with Geometry Script.
Procedural Content Generation (PCG): author and execute PCG graph assets.
Gameplay Systems:
Gameplay Abilities (GAS): abilities, effects, attributes.
Characters & Combat: creation, movement, weapons, projectiles, damage, melee.
AI: controllers, Behavior Trees, EQS, perception, State Trees, Smart Objects, NavMesh/pathfinding.
Inventory & Interaction: items, equipment, loot, crafting, interactables, destructibles, triggers.
Networking: replication, RPCs, network prediction, sessions, split-screen, and input mappings.
System & Tooling: execute console commands, CVars; run Unreal Build Tool (UBT) and tests; manage project settings; execute Python scripts; inspect runtime objects; read logs.
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 "Install 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.
Unreal Engine MCP Server
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal Engine through a native C++ Automation Bridge plugin. Built with TypeScript and C++.
Table of Contents
Related MCP server: unreal-mcp
Features
Category | Capabilities |
Asset Management | Browse, import, duplicate, rename, delete assets; create materials |
Actor Control | Spawn, delete, transform, physics, tags, components |
Editor Control | PIE sessions, camera, viewport, screenshots, bookmarks |
Level Management | Load/save levels, streaming, lighting |
Animation & Physics | Animation BPs, state machines, ragdolls, vehicles, constraints |
Visual Effects | Niagara particles, GPU simulations, procedural effects, debug shapes |
Sequencer | Cinematics, timeline control, Movie Render Queue, media, Take Recorder, replay |
Graph Editing | Blueprint, Niagara, Material, and Behavior Tree graph manipulation |
Audio | Sound cues, audio components, sound mixes, ambient sounds |
System | Console commands, UBT, tests, logs, project settings, CVars |
Architecture
Native C++ Automation — All operations route through the MCP Automation Bridge plugin
Dual Transport — Native HTTP/SSE (no bridge needed) or WebSocket via TypeScript bridge
Dynamic Type Discovery — Runtime introspection for lights, debug shapes, and sequencer tracks
Graceful Degradation — Server starts even without an active Unreal connection
On-Demand Connection — Retries automation handshakes with exponential backoff
Command Safety — Blocks dangerous console commands with pattern-based validation
Capability Token Auth — On-by-default token authentication (auto-generated 32-byte secret at
<Project>/Saved/MCP/capability-token) for both WS and HTTP transports; manualCapabilityTokenin Project Settings overrides the fileAsset Caching — 10-second TTL for improved performance
Metrics Rate Limiting — Per-IP rate limiting (60 req/min) on Prometheus endpoint
Centralized Configuration — Unified class aliases and type definitions
Getting Started
Prerequisites
Node.js 20.19 or later (Node.js 18 is not supported) — required for the TypeScript stdio bridge. Not needed for the native MCP transport.
Step 1: Install MCP Server (Option B only — skip for Native MCP)
Skip this step if using Option A: Native MCP Transport (Step 4A below).
NPX (Recommended):
npx unreal-engine-mcp-serverClone & Build:
git clone https://github.com/ChiR24/Unreal_mcp.git
cd Unreal_mcp
npm install
npm run build
node dist/cli.jsStep 2: Install Unreal Plugin
The MCP Automation Bridge plugin is included at Unreal_mcp/plugins/McpAutomationBridge.
From source (requires a project with code target)
Your project must have a code target (.sln or .xcworkspace).
Blueprint-only projects cannot compile native plugins — to convert, add any class via Tools > New C++ Class in the editor.
Method 1: Copy Folder
Copy: Unreal_mcp/plugins/McpAutomationBridge/
To: YourUnrealProject/Plugins/McpAutomationBridge/Method 2: External Plugin Directory (no copy needed)
Open Unreal Editor → Edit → Plugins
Click Plugin Directories (bottom-left)
In Additional Plugin Directories, add the path to
Unreal_mcp/plugins/Restart the editor — the plugin will be picked up from the external location
This saves the path in your .uproject file so the plugin stays linked without copying.
The plugin compiles automatically when you open the project — UE detects the .uplugin + Source/ and runs UnrealBuildTool.
Video Guide:
https://github.com/user-attachments/assets/d8b86ebc-4364-48c9-9781-de854bf3ef7d
⚠️ First-Time Project Open: UE may prompt "Would you like to rebuild them now?" — click Yes. If instead you see "Missing Modules — McpAutomationBridge. Engine modules cannot be compiled at runtime. Please build through your IDE." — open your project in Visual Studio (Win) or Xcode (Mac) and build from there. After that, the editor will open normally with the plugin loaded.
Pre-built (works with any project, including Blueprint-only)
Build the plugin once, then distribute the compiled binaries — no IDE or compilation needed on the target machine.
1. Build:
# macOS / Linux
./scripts/package-plugin.sh /path/to/UE_5.6
# Windows
scripts\package-plugin.bat C:\Path\To\UE_5.6This produces a zip like McpAutomationBridge-v0.5.30-UE5.7-Linux.zip.
2. Install: unzip into YourProject/Plugins/ and open the project. That's it — no compilation step.
Note: pre-built binaries are tied to a specific UE version. A build for 5.6 won't work with 5.5, 5.7, or 5.8.
Step 3: Enable Required Plugins
Enable via Edit → Plugins, then restart the editor.
Plugin | Required For |
MCP Automation Bridge | All automation operations |
Python Editor Script Plugin | Python-backed editor automation helpers |
Editor Scripting Utilities | Asset/Actor subsystem operations |
Niagara | Visual effects and particle systems |
Gameplay Abilities |
|
Smart Objects | AI smart object operations |
Plugin | Required For |
Level Sequence Editor |
|
Movie Render Pipeline |
|
Movie Pipeline Mask Render Pass | Object-ID render pass |
Takes |
|
Electra Player |
|
Control Rig |
|
GeometryScripting |
|
Behavior Tree Editor |
|
Niagara Editor | Niagara authoring |
Environment Query Editor | AI/EQS operations |
MetaSound |
|
StateTree |
|
Enhanced Input |
|
Chaos Cloth | Cloth simulation |
Interchange | Asset import/export |
Data Validation | Data validation |
PCG |
|
Procedural Mesh Component | Procedural geometry |
OnlineSubsystem | Session/networking operations |
OnlineSubsystemUtils | Session/networking operations |
💡 Optional plugins are auto-enabled by the MCP Automation Bridge plugin when needed. PCG support is compiled for source projects when the project explicitly enables PCG. Versioned release packages for UE 5.2+ include PCG support. All Unreal Engine versions from 5.0 to 5.8 are supported and working.
Step 4: Configure MCP Client
Option A: Native MCP Transport (Direct HTTP — no bridge needed)
The plugin includes a built-in MCP Streamable HTTP server. AI clients connect directly to the plugin over HTTP — no TypeScript bridge, no Node.js, no npm.
Note: the bAllowNonLoopback setting now applies to both the WebSocket bridge and the native MCP transport. Enabling it binds both surfaces to non-loopback addresses. If you only need LAN access for the WebSocket bridge, do not enable bAllowNonLoopback and instead expose the bridge via a reverse proxy. Capability token auth is on by default (0.5.30+) — both transports require authentication automatically. A manually configured CapabilityToken in Project Settings or the auto-generated token at <Project>/Saved/MCP/capability-token is used automatically.
Enable in Unreal:
Edit > Project Settings > Plugins > MCP Automation Bridge
Check Enable Native MCP
Set port (default:
3000)Optionally set Native MCP Instructions for project-specific guidance
Restart the editor
Configure your MCP client to use Streamable HTTP transport at:
http://localhost:3000/mcpClaude Code:
claude mcp add unreal-engine --transport http http://localhost:3000/mcpOr manually in ~/.claude/settings.json or project .mcp.json:
{
"mcpServers": {
"unreal-engine": {
"type": "url",
"url": "http://localhost:3000/mcp"
}
}
}Cursor (.cursor/mcp.json):
{
"mcpServers": {
"unreal-engine": {
"url": "http://localhost:3000/mcp"
}
}
}Verify it works:
Status bar — look for
● MCP :3000 (2)in the bottom-right of the editor. Green dot = server running, number in parens = active sessions. Click it to open settings.Output Log — filter by
LogMcpNativeTransportto see connections, tool calls, and session activity:LogMcpNativeTransport: Native MCP server started on http://localhost:3000/mcp LogMcpNativeTransport: MCP session initialized: ... (client: claude-code 2.1.92, active sessions: 1) LogMcpNativeTransport: tools/call: inspect (RequestId=...) LogMcpNativeTransport: tools/call completed: ... (tool=inspect, success=true)
Features:
SSE streaming for real-time progress during long operations
Multiple concurrent sessions (Cursor + Claude Code + others simultaneously)
Dynamic tool management — core tools load by default, enable more via
manage_toolsPython execution via
execute_pythonaction (inline code or .py files)Capability token authentication — on by default (auto-generated secret at
<Project>/Saved/MCP/capability-token; manualCapabilityTokenin Project Settings overrides)
Option B: TypeScript Bridge (stdio — classic setup)
Add to your Claude Desktop / Cursor config file:
Using Clone/Build:
{
"mcpServers": {
"unreal-engine": {
"command": "node",
"args": ["path/to/Unreal_mcp/dist/cli.js"],
"env": {
"UE_PROJECT_PATH": "C:/Path/To/YourProject",
"MCP_AUTOMATION_PORT": "8091"
}
}
}
}Using NPX:
{
"mcpServers": {
"unreal-engine": {
"command": "npx",
"args": ["unreal-engine-mcp-server"],
"env": {
"UE_PROJECT_PATH": "C:/Path/To/YourProject"
}
}
}
}Configuration
Environment Variables
# Required
UE_PROJECT_PATH="C:/Path/To/YourProject"
# Automation Bridge
MCP_AUTOMATION_HOST=127.0.0.1
MCP_AUTOMATION_PORT=8091
# LAN Access (optional)
# SECURITY: Set to true to allow binding to non-loopback addresses (e.g., 0.0.0.0)
# Only enable if you understand the security implications.
MCP_AUTOMATION_ALLOW_NON_LOOPBACK=false
# Logging
LOG_LEVEL=info # debug | info | warn | error
# Optional
MCP_CONNECTION_TIMEOUT_MS=5000
MCP_REQUEST_TIMEOUT_MS=120000
ASSET_LIST_TTL_MS=10000
# Optional Prometheus metrics endpoint
# Loopback-only by default. Non-loopback metrics requires both explicit opt-in and a token.
# MCP_METRICS_PORT=9100
# MCP_METRICS_HOST=127.0.0.1
# MCP_METRICS_ALLOW_NON_LOOPBACK=false
# MCP_METRICS_TOKEN=change-me
# Custom content mount points (comma-separated)
# Plugins with CanContainContent register mount points beyond /Game/.
# MCP_ADDITIONAL_PATH_PREFIXES=/ProjectObject/,/ProjectAnimation/LAN Access Configuration
By default, the automation bridge only binds to loopback addresses (127.0.0.1) for security. To enable access from other machines on your network:
TypeScript (MCP Server):
MCP_AUTOMATION_ALLOW_NON_LOOPBACK=true
MCP_AUTOMATION_HOST=0.0.0.0Unreal Engine Plugin:
Go to Edit → Project Settings → Plugins → MCP Automation Bridge
Under Security, enable "Allow Non Loopback"
Under Connection, set "Listen Host" to
0.0.0.0Restart the editor
⚠️ Security Warning: Enabling LAN access exposes the automation bridge to your local network. Only use on trusted networks with appropriate firewall rules. Enable capability token authentication (Require Capability Token in project settings) to prevent unauthorized access when using LAN mode.
Available Tools
The MCP server exposes a single unreal gateway tool. The 23 canonical parent tools are internal and reachable exclusively through the gateway's four operations: search, describe, execute, and configure.
Gateway Workflow
search— discover available tools by keyword, category, or action namedescribe— get the exact contract (actions, parameters, schema) for a specific toolexecute— run one validated action on a canonical toolconfigure— manage internal tool enable/disable state (wrapsmanage_tools)
Example call:
{
"operation": "search",
"query": "asset"
}Then:
{
"operation": "describe",
"tool": "manage_asset",
"action": "import_asset"
}Then:
{
"operation": "execute",
"tool": "manage_asset",
"action": "import_asset",
"params": { "sourcePath": "/path/to/asset.fbx", "destinationPath": "/Game/Imported/asset" }
}Migration from direct tool calls
The single unreal gateway is permanent on both transports; there is no opt-out and no legacy 23-tool listing to restore. A client that still calls a canonical tool name directly (tools/call with name: "manage_asset", name: "control_actor", etc.) receives a bounded, copy-paste-executable DIRECT_TOOL_CALL_REMOVED receipt instead of a routed call. The receipt carries a nextCall that drills exactly one level: { "operation": "search" } for an unknown name, { "operation": "describe", "tool": "<tool>" } when no action was supplied, or { "operation": "execute", "tool": "<tool>", "action": "<action>", "params": { ... } } when the direct call already named an action. Run that nextCall through the unreal tool to finish the migration.
Gateway Protocol & Transport
Both transports expose the same unreal gateway contract, but they are separate lifecycles. Do not route around their boundaries.
TypeScript stdio transport —
node dist/cli.jstalks to the Unreal plugin over a WebSocket bridge. It permanently exposes the singleunrealgateway tool; there is no gateway-mode toggle.Native MCP transport — the plugin's built-in Streamable HTTP/SSE server at
/mcp(no Node.js, no bridge). The native MCP surface permanently exposes the same singleunrealgateway tool; there is no gateway-mode toggle.
Both surfaces negotiate the MCP protocol version at initialize; the supported set is intentionally asymmetric. The native /mcp transport supports exactly the three modern versions 2025-11-25, 2025-06-18, and 2025-03-26, and deliberately does not implement the later 2026-07-28 RC. The TypeScript stdio server also accepts the two legacy versions 2024-11-05 and 2024-10-07, so the native surface is intentionally stricter. Both negotiate down to the highest mutually supported version (2025-11-25 is the latest). See docs/protocol.md for the full negotiation and transport contract, including the MCP-Protocol-Version header guard (HTTP 400 on invalid), cancellation semantics, and progressToken handling.
Internal Canonical Tools (23)
The gateway hides these 23 canonical parent tools. They are listed here for reference:
Tool | Description |
| Assets, Materials, Render Targets, Behavior Trees, Blueprint Struct (UserDefinedStruct) authoring |
| Blueprints, SCS components, graph editing, UMG widgets, layout, bindings, animations |
| Spawn, delete, transform, physics, tags |
| PIE, Camera, viewport, screenshots |
| Load/save, streaming, lighting |
| UBT, Tests, Logs, Project Settings, CVars, Python Execution |
| Object Introspection |
| Dynamic tool management (enable/disable at runtime) |
Tool | Description |
| Landscapes, foliage, procedural terrain, lighting, spline roads/rivers/fences |
| Levels, sublevels, World Partition, streaming, data layers, HLOD, volumes |
| Procedural mesh creation and editing with Geometry Script |
| PCG graph assets, subgraphs, input/sampler/filter/spawner nodes, pin connections, execution, partition grid size, and node settings |
Tool | Description |
| Animation BPs, skeletons, sockets, physics assets, cloth, vehicles, ragdolls, Control Rig, IK |
| Niagara, particles, debug shapes, GPU simulations |
| Gameplay Ability System: abilities, effects, attributes |
| Character creation, movement, advanced locomotion |
| Weapons, projectiles, damage, melee combat |
| AI controllers, Behavior Trees, EQS, perception, State Trees, Smart Objects, NavMesh/pathfinding |
| Items, equipment, loot tables, crafting |
| Interactables, destructibles, triggers |
Tool | Description |
| Audio Assets, Components, Sound Cues, MetaSounds, Attenuation |
| Sequencer, cinematics, Movie Render Queue, media playback, Take Recorder, and replay controls |
| Replication, RPCs, network prediction, sessions, split-screen, LAN/voice, game framework, input mappings |
Blueprints • Materials • Textures • Static Meshes • Skeletal Meshes • Levels • Sounds • Particles • Niagara Systems • Behavior Trees
Docker
docker build -t unreal-mcp .
docker run -it --rm -e UE_PROJECT_PATH=/project unreal-mcpDocumentation
Document | Description |
TypeScript to C++ routing | |
C++ plugin architecture | |
How to run and write tests | |
Development roadmap |
Development
npm run build # Clean + compile TypeScript to dist/
npm run lint # Run ESLint 9 (fail on any warning)
npm run type-check # tsc --noEmit
npm run test:unit # Vitest unit tests (no Unreal required)
npm run test:smoke # Offline mock in-memory MCP check (needs built dist/)
npm run manifest:check # Fail if generated gateway manifest artifacts drift
npm run test:native-parity # TS vs native canonical tool/action equality
npm run test:params # Parity + strict parameter audit
npm run version:check # Assert all version sources agree
npm test # Integration suite (needs a live Unreal Editor + bridge)Gateway manifest generation
The neutral gateway manifest is generated from src/tools/catalog/consolidated-tool-definitions.ts into three artifacts (runtime .ts/.json plus the native .h). Never hand-edit the generated files.
node --loader ts-node/esm scripts/generate-gateway-manifest.ts # regenerate
node --loader ts-node/esm scripts/generate-gateway-manifest.ts --check # CI gate: fail on driftCI gates
CI runs, in order: ESLint 9 (npx eslint . --max-warnings=0), TypeScript type-check, unit tests, registry:check, normalization:check, manifest:check, policy:check, native parity + parameter audit (test:params), migration:check, primitives:check, security:check, eval:check, version:check, workflow:check, then a blocking runtime-only dependency audit (npm audit --omit=dev --audit-level=high) followed by an informational full-tree npm audit --audit-level=moderate. A plugin packaging job runs scripts/package-plugin.sh only when an Unreal Engine source root secret is provided (opt-in), because CI runners do not ship an engine. Release archives exclude Binaries/, Intermediate/, and Saved/ so generated build dirs never leak.
Community
Resource | Description |
Track roadmap progress and priorities | |
Ask questions, share ideas, get help | |
Report bugs and request features |
Contributing
Contributions welcome! Please:
Include reproduction steps for bugs
Keep PRs focused and small
Follow existing code style
License
MIT — See LICENSE
Available Tools
1 toolunrealAInspect
Unreal Engine capability gateway. Search first, describe the exact contract, then execute a validated action. Use configure only to manage internal capability availability.
| Name | Required | Description | Default |
|---|---|---|---|
| tool | No | Exact canonical parent tool name returned by search or describe. | |
| limit | No | Maximum search results to return. Defaults to 12. | |
| param | No | 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. | |
| query | No | Search words for tools, categories, descriptions, or actions. | |
| action | No | Exact action name returned by describe. For configure, this is a manage_tools action. | |
| cursor | No | Opaque search cursor from a previous response nextCursor. Supersedes offset. | |
| domain | No | Capability domain to browse or filter by. Call describe with no selector to list domains. | |
| effect | No | Filter search results by declared behavior effect. | |
| family | No | Capability family inside a domain. Call describe with a domain to list its families. | |
| offset | No | Zero-based search result offset. Defaults to 0. | |
| params | No | Parameters for execute or configure. Keys are the action-specific parameter names returned by describe. Never include action or subAction here. | |
| consent | No | 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. | |
| maxBytes | No | Serialized byte ceiling for a search response. Results are dropped from the end until the response fits. | |
| operation | Yes | search finds capabilities. describe returns an exact parent-tool contract. execute runs one validated action. configure manages internal capability availability. | |
| capability | No | Exact canonical capability ID (or declared alias) returned by search, e.g. asset.import. Preferred selector for describe. |
Output Schema
| Name | Required | Description |
|---|---|---|
| cost | No | |
| data | No | Execute payload projected against the capability's declared output schema. Same value as receipt.data, and the same location the native /mcp surface publishes. |
| tool | No | |
| error | No | |
| limit | No | |
| param | No | |
| scope | No | Catalog scope: 'tool' for a tool summary, 'union' for the tool-union parameter catalog. |
| total | No | |
| action | No | |
| domain | No | |
| family | No | |
| hashes | No | Per-record schema and content hashes from the generated catalog. |
| offset | No | |
| policy | No | |
| result | No | |
| schema | No | Full schema of the single described param. |
| actions | No | Paginated/filterable action list on tool-only describe. |
| domains | No | Bounded domain list on a catalog-level describe. |
| filters | No | Filters applied to this search. |
| hasMore | No | |
| message | No | |
| outputs | No | |
| reasons | No | |
| results | No | |
| success | Yes | |
| behavior | No | |
| families | No | Bounded family list on a domain-level describe. |
| maxBytes | No | |
| nextCall | No | Directly-invokable gateway request for guided self-correction. |
| required | No | Whether the described param is required. |
| runnable | No | False when the capability cannot currently be executed; nextCall then points at the fix. |
| drillDown | No | Example nextCall payload to drill one level deeper. |
| errorCode | No | |
| operation | Yes | |
| truncated | No | True when results were dropped to fit the byte budget. |
| capability | No | Canonical capability ID this response describes. |
| nextCursor | No | Cursor to pass back as cursor to continue a search. |
| parameters | No | Paginated/filterable compact parameter catalog on tool+action describe. |
| parentTool | No | Legacy parent tool that dispatches the described capability. |
| actionCount | No | |
| actionLimit | No | |
| deprecation | No | |
| inputSchema | No | Exact input schema of the described capability. Never a parent-tool union. |
| suggestions | No | Closest-match names for an invalid tool/action/param call. |
| actionOffset | No | |
| availability | No | Whether the capability is available, disabled or unavailable, and why. |
| capabilities | No | Bounded capability list on a family-level describe. |
| consentGrant | No | Exact consent grant this capability requires, ready to pass back as the execute call's consent sibling. Absent when policy.consent is 'none'. |
| migratedFrom | No | Legacy tool/action pair that resolved to this capability. |
| outputSchema | No | Exact output schema of the described capability. |
| actionHasMore | No | |
| parameterCount | No | |
| parameterLimit | No | |
| catalogRevision | No | Revision of the generated canonical capability catalog this response was served from. |
| parameterOffset | No | |
| availableActions | No | |
| parameterHasMore | No | |
| perActionSchemas | No | |
| resolvedFromAlias | No | Declared alias that resolved to this capability. |
| availableParameters | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It does not mention that execute may have side effects, that destructive capabilities require consent, or any safety or reusability constraints. The description is too terse for a tool that can trigger actions.
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?
Two sentences, front-loaded with the core purpose, and every word adds value. No redundant information.
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?
Given the tool's complexity (15 parameters, nested objects, output schema), the description provides the essential workflow but omits broader context like the safety implications of execute, consent requirements, or how actions are validated. The schema covers details, but the description alone is not fully complete for a gateway of this scope.
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?
Schema coverage is 100%, so the schema already documents all parameters including operation, search, describe, execute, configure, and consent. The description adds no parameter semantics beyond the schema, but the baseline of 3 applies because the schema does the heavy lifting.
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 'Unreal Engine capability gateway' clearly identifies it as a meta-tool for accessing capabilities, and the workflow 'Search first, describe the exact contract, then execute' clarifies its primary function. It is distinct enough even without sibling tools, though it doesn't use a specific verb+resource pattern.
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?
The description explicitly instructs the usage order: 'Search first, describe the exact contract, then execute a validated action.' It also provides a specific exclusion: 'Use configure only to manage internal capability availability.' This is clear when-to-use and when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
With only one tool, there is no possibility of confusing it with another tool. The 'unreal' gateway is the sole entry point, so agents cannot misselect between overlapping functions in the tool set.
The tool name 'unreal' is a bare noun and does not follow any verb_noun or action-oriented pattern. While there is only one tool, the name lacks consistency with typical MCP naming conventions and provides no hint of its function.
A single tool for an 'Unreal Engine capability gateway' suggests the server is covering a large domain through one catch-all interface. This feels too thin for the apparent scope, as agents would benefit from separate tools for distinct operations like execution or configuration.
The gateway description claims to support search, describe, execute, and configure, but it is unclear whether all necessary Unreal Engine operations are reachable or discoverable. The lack of explicit tool definitions creates significant gaps in the agent's ability to know what actions are available without probing the gateway repeatedly.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Give your AI agents the tools to build, manage, and run automation workflows.
Turns a phone into a camera+Bluetooth remote so AI assistants can see and control any PC.
Generate game-ready 3D models, textures, and audio from natural language, over MCP.
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
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.2951MIT
- FlicenseCqualityDmaintenanceEnables 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.1006
- AlicenseAqualityDmaintenanceEnables AI assistants to interact with Unreal Engine via Remote Control API for actor, asset, level, and editor operations.2216MIT
- 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.295MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ChiR24/Unreal_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server