Model Context Protocol for Unreal Engine

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

What is Unreal MCP?

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

How to use Unreal MCP?

To use Unreal MCP, set up the Unreal Engine project with the provided plugin, configure your MCP client, and use natural language commands to control Unreal Engine functionalities.

Key features of Unreal MCP?

  • Actor management: Create, delete, and manipulate actors in Unreal Engine.
  • Blueprint development: Create and manage Blueprint classes and components.
  • Editor control: Focus on specific actors and control viewport settings.
  • Natural language commands: Control Unreal Engine workflows using AI assistants.

Use cases of Unreal MCP?

  1. Automating game development tasks in Unreal Engine.
  2. Enhancing productivity for developers using AI assistants.
  3. Simplifying the control of complex Unreal Engine functionalities.

FAQ from Unreal MCP?

  • Is Unreal MCP stable for production use?

No, Unreal MCP is currently in an experimental state and not recommended for production use.

  • What are the prerequisites for using Unreal MCP?

You need Unreal Engine 5.5+, Python 3.12+, and an MCP client like Claude Desktop, Cursor, or Windsurf.

  • How can I get started with Unreal MCP?

You can start by using the sample project provided in the MCPGameProject directory.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
chongdashu
Star
507
Language
C++
License
-

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

a day ago