Chrrxs/robloxstudio-mcp

What it solves

This project bridges the gap between AI coding assistants and Roblox Studio. It allows developers to use LLM-powered agents to directly interact with, debug, and automate the Roblox game development environment, removing the need for manual context switching between an AI chat interface and the game engine.

How it works

It implements the Model Context Protocol (MCP) to create a secure communication channel between an MCP-compliant AI client (like Claude Code or Cursor) and a custom Roblox Studio plugin. The plugin exposes a suite of tools that the AI can invoke to perform actions such as executing Luau code, managing playtest sessions, reading logs, capturing performance profiles, and modifying game assets.

Who it’s for

This is for Roblox developers who want to integrate AI agents into their workflow to speed up debugging, automate repetitive engine tasks, or perform complex script analysis and performance profiling.

Highlights

• Live Debugging: Execute Luau code in real-time server or client contexts and instrument code with non-pausing breakpoints.
• Automated Testing: Programmatically start, stop, and inspect solo or multiplayer playtest sessions.
• Performance Analysis: Capture CPU timings, memory breakdowns, and scene analysis reports directly through the agent.
• Asset Management: Search, preview, and insert assets from the Creator Store with automated security and cleanup steps.
• Studio Control: Manage instance properties, script text, and viewport captures (screenshots) via natural language commands.