"Unreal Engine" matching MCP servers:

A code understanding and generation system designed for Galacean Engine that helps LLMs comprehend the engine architecture and generate high-quality engine code based on user intent.

A TypeScript MCP server that lets AI assistants interact with the Godot 4.x game engine: not just editing files, but playing the game.

Provides coding agents with persistent, evidence-backed project memory and knowledge across sessions, using a structured memory tree and local knowledge base.

Sovereign, deterministic, local-first context and DAG lifecycle engine with native stdio MCP server for autonomous AI coding agents.

Enables agents to generate typed client code from OpenAPI, GraphQL, Protobuf, and SQL specs using MetaEngine's code-generation platform.

Turn the AI you already use into a game studio. Describe a game and Claude or Cursor builds it as a real 3D browser game: playable immediately, hosted on its own link, shareable with anyone. No engine, no build step, no code knowledge, nothing to export. Your AI ships the whole thing: it pulls free 3D assets, rigs characters, and playtests its own build until the game works. Free to start.

A local project intelligence, batch coding, and self-learning engine for Codex that enables task-level batch coding, reduces token usage, and automatically learns skills.

Enables AI agents to build games with the Cocos4 engine by providing high-level scaffolding tools and transparently proxying native MCP tools.

MCP servers that let Claude Code delegate to other coding CLIs (Copilot, Codex, Gemini) for cross-model second opinions, structured reviews, and multi-engine consultations.

AI-native open-source 2D game engine whose MCP server exposes every editor operation to coding agents as typed commands, so an agent can build, run, and verify a game inside the editor. It runs locally on macOS, Windows, and Linux with no cloud service or API key.

An autonomous MCP server for AI-powered software generation using Gemini and Groq, with features like dual-engine strategy, visual inspection, and QA sentinel.

Enables AI assistants to create and edit 3D scenes, geometry, scripts, and builds in the Forma engine, with changes reflected live in the editor.

Connects AI assistants to a local Codex engine for performing deep, project-level code reviews and automated refactoring. It enables context-aware bug fixes and multi-file analysis through a standardized bridge between modern AI clients and local development environments.

self-hosted development harness (Go engine + CLI + desktop, Linux first) · brief → requirements → spec → plan → build → review → release · verdicts are exit codes, never model opinions · local models first (llama.cpp, vLLM) beside any OpenAI-compatible or Anthropic endpoint · operable by humans or by other agents over MCP with recorded, attributed decisions

Enables a persona-driven coding pair programmer to plan and execute code work through a full MCP tool loop, merging servers for image generation, live web search and fetch, a persistent shell with file access, audio/video processing, and hundreds of third-party app integrations like Gmail, Slack, GitHub, and Drive. Long conversations are automatically compressed to stay inside the engine's context window, tool calls are billed to the caller's own Pollen, and the whole agent runs on a single engine chosen because it can actually emit tool calls.