"Understanding Inference Models" matching MCP servers:

An MCP server that enables LLMs to build physically valid Lego models by enforcing catalog-only parts, no overlaps, stud-to-tube connections, and other real-world constraints.

Provides AI coding assistants with access to AccelByte Gaming Services (AGS) Extend SDK functions and models through searchable symbols and detailed documentation. Helps generate SDK code by exposing context about available functions, models, and templates for creating Extend app projects across multiple languages (Go, C#, Java, Python).

Enables LLM agents to play full games of Civilization VI by connecting to running game instances via the FireTuner debug interface, with 76 tools for units, cities, diplomacy, research, and turn management, plus narration of game state through rule-enforcing APIs without requiring vision models.

Enables Large Language Models to play chess agentically with real-time HTML board visualization and a hybrid AI engine featuring ten difficulty levels. It supports interactive games between users and agents, including a web dashboard to monitor active matches.

Enables tool-using language models to play Lemonade Tycoon Deluxe as a text-only business benchmark, exposing game UI state and actions as semantic MCP tools without vision or shell access.

An MCP server for the Pyxel retro game engine that enables AI models to autonomously run, verify, and iterate on retro game programs. It includes tools for visual verification through screenshots, sprite and layout analysis, and audio rendering.

Enables exploring Steam store reviews and community discussion threads with server-side filtering, temporal analysis, and metadata context for understanding player sentiment and feedback beyond store page noise.

Enables AI assistants to create complete, Teardown-ready multi-part .vox voxel models with material palette compatibility, previews, manifests, and XML skeletons so they can write coherent mod files.

Enables searching, retrieving, and managing CC0 GLB 3D models and asset packs, including listing categories, tags, licenses, demos, and submitting or updating assets with API key authentication.

Enables AI assistants to build Minecraft models, textures, and animations directly inside Blockbench through the Model Context Protocol.

Enables AI models to play the game Peggle by capturing the primary monitor's screen and simulating mouse clicks. It provides tools for visual analysis and coordinate-based interaction to automate gameplay.

Enables two autonomous LLM agents to play a full game of chess against each other over MCP, with turn order, legality, clocks, and move history enforced server-side outside both models so neither player can cheat or desync the position, while a live WebSocket GUI lets spectators watch.

Enables AI to control Blockbench for creating and editing 3D models, especially Minecraft-style pets, weapons, and animations, through structured MCP tools and reference image processing.

Provides an MCP runtime that turns Roblox Studio into an AI-native, autonomous, bidirectional development platform, letting AI assistants create and edit scenes, models, animations, scripts, and game systems through 63+ tools. It integrates with the official Roblox Studio MCP and uses 11 specialized providers for modeling, animation, Luau, testing, and diagnostics.

Enables AI models to develop and automate RPG Maker MZ projects by creating maps, events, and plugins through natural language commands. It provides comprehensive tools for database management, asset integrity checks, and direct map tile manipulation.

Enables generating game-ready 3D models, textures, and audio from natural language by proxying to the remote Gessa API.

Enables vision-capable models to play Pokemon Emerald through mGBA by providing screenshots, OCR dialogue transcription, movement and button controls, and persistent session journals.

Enables AI models and human players to play tic-tac-toe together through MCP, with server-enforced rules, turn-based waiting, and live board state via tools, resources, and prompts.

Enables AI assistants to build, texture, animate, and export Minecraft/GeckoLib cube models inside Blockbench via the Model Context Protocol.

Enables tool-calling AI models to play Steam Balatro through a local STDIO connection, exposing only information a human player could see while validating and executing native game actions and confirming their results. It also persists, reloads, and revises the model's accumulated experience across sessions.