Production-ready MCP server for Unreal Engine with comprehensive game development tools
If you already use Unreal, the unreal mcp server is the piece that lets your assistant work with it directly. Production-ready MCP server for Unreal Engine with comprehensive game development tools.
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++.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
manage_asset — Assets, Materials, Render Targets, Behavior Trees, Blueprint Struct (UserDefinedStruct) authoringmanage_blueprint — Blueprints, SCS components, graph editing, UMG widgets, layout, bindings, animationscontrol_actor — Spawn, delete, transform, physics, tagscontrol_editor — PIE, Camera, viewport, screenshotsmanage_level — Load/save, streaming, lightingsystem_control — UBT, Tests, Logs, Project Settings, CVars, Python Executioninspect — Object Introspectionmanage_tools — Dynamic tool management (enable/disable at runtime)build_environment — Landscapes, foliage, procedural terrain, lighting, spline roads/rivers/fencesmanage_level_structure — Levels, sublevels, World Partition, streaming, data layers, HLOD, volumesmanage_geometry — Procedural mesh creation and editing with Geometry Scriptmanage_pcg — PCG graph assets, subgraphs, input/sampler/filter/spawner nodes, pin connections, execution, partition grid size, and node settingsunreal-engine-mcp-server on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
Configuration is passed through the environment: UE_PROJECT_PATH, MCP_AUTOMATION_PORT, MCP_AUTOMATION_HOST, MCP_METRICS_HOST, MCP_METRICS_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of monitoring and observability servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Unreal's toolset — manage_asset, manage_blueprint, control_actor and 11 more — is a fair guide to whether it matches your workflow. It is maintained by ChiR24; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| manage_asset | Assets, Materials, Render Targets, Behavior Trees, Blueprint Struct (UserDefinedStruct) authoring |
| manage_blueprint | Blueprints, SCS components, graph editing, UMG widgets, layout, bindings, animations |
| control_actor | Spawn, delete, transform, physics, tags |
| control_editor | PIE, Camera, viewport, screenshots |
| manage_level | Load/save, streaming, lighting |
| system_control | UBT, Tests, Logs, Project Settings, CVars, Python Execution |
| inspect | Object Introspection |
| manage_tools | Dynamic tool management (enable/disable at runtime) |
| build_environment | Landscapes, foliage, procedural terrain, lighting, spline roads/rivers/fences |
| manage_level_structure | Levels, sublevels, World Partition, streaming, data layers, HLOD, volumes |
| manage_geometry | Procedural mesh creation and editing with Geometry Script |
| manage_pcg | PCG graph assets, subgraphs, input/sampler/filter/spawner nodes, pin connections, execution, partition grid size, and node settings |
| animation_physics | Animation BPs, skeletons, sockets, physics assets, cloth, vehicles, ragdolls, Control Rig, IK |
| manage_effect | Niagara, particles, debug shapes, GPU simulations |
**Cursor** (`.cursor/mcp.json`):
```json
{
"mcpServers": {
"unreal-engine": {
"url": "http://localhost:3000/mcp"
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| UE_PROJECT_PATH | Filesystem location the server is allowed to use. | Optional |
| MCP_AUTOMATION_PORT | Configuration value read at startup. | Optional |
| MCP_AUTOMATION_HOST | Endpoint or connection string the server talks to. | Optional |
| MCP_METRICS_HOST | Endpoint or connection string the server talks to. | Optional |
| MCP_METRICS_TOKEN | Credential the server authenticates with. | Yes |
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.
Errors with full context — stack traces, issue triage and AI-powered root-cause analysis from Sentry's server.
Enables enhanced web research capabilities for large language models through intelligent search queuing and advanced content extraction.
Automates browser interactions and enables Large Language Models (LLMs) to interact with web pages through Playwright and Chrome DevTools Protocol
Guides tool usage by providing recommendations for MCP tools at each problem-solving stage.