Unreal Engine
This MCP server provides comprehensive Unreal Engine integration through Python Remote Execution, enabling AI assistants to interact with Unreal Editor instances for game development workflows. Built by RUNREAL using TypeScript and the official MCP SDK, it offers 18 specialized tools including asset management (listing, searching, validation, export), world manipulation (creating, updating, deleting objects with transform controls), project analysis (asset counts, map information, world outliner), and editor utilities (console commands, screenshots, Python script execution). The implementation uses the unreal-remote-execution library to establish real-time connections with running Unreal Editor instances, automatically handling connection retries and providing template-based Python script generation for complex operations, making it valuable for game developers who need AI assistance with level design, asset organization, debugging workflows, and automated content creation tasks.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- maps-location
- Source
- PulseMCP
- Repository
- github.com/runreal/unreal-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Unreal Engine from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.