# unreal-mcp

> unreal-mcp — chongdashu-unreal-mcp. Use this tool when you need to control Unreal Engine using natural language inputs, enabling AI assistants like Cursor, Windsurf, and Claude Desktop to interact with the engine seamlessly. It solves problems of manual engine control, allowing for more intuitive and efficient workflows through the Model Context Protocol (MCP). Ideal for use cases where voice or text commands can enhance productivity in Unreal Engine projects.

Canonical page: https://skillsregistry.net/skills/chongdashu-unreal-mcp  
JSON: https://api.skillsregistry.net/v1/skills/chongdashu-unreal-mcp

## Description

Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).

## Trust

- **Trust score (0–1):** 0.94
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/chongdashu/unreal-mcp)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "chongdashu-unreal-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/chongdashu-unreal-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/chongdashu-unreal-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt