Roblox Studio MCP Server
Provides AI assistants with comprehensive access to Roblox Studio projects for exploration, script analysis, debugging, and bulk editing.
Roblox Studio MCP Server
Connect AI assistants like Claude and Gemini to Roblox Studio
What is This?
An MCP server that lets AI explore your game structure, read/edit scripts, and perform bulk changes all locally and safely.
Setup
- Install the Studio plugin to your Plugins folder
- Enable Allow HTTP Requests in Experience Settings > Security
- Connect your AI:
Claude Code:
claude mcp add robloxstudio -- npx -y robloxstudio-mcp@latest
Codex CLI:
codex mcp add robloxstudio -- npx -y robloxstudio-mcp@latest
Gemini CLI:
gemini mcp add robloxstudio npx --trust -- -y robloxstudio-mcp@latest
Plugin shows "Connected" when ready.
Other MCP clients (Claude Desktop, Cursor, etc.)
{
"mcpServers": {
"robloxstudio-mcp": {
"command": "npx",
"args": ["-y", "robloxstudio-mcp@latest"]
}
}
}
Windows users: If you encounter issues, use cmd:
{
"mcpServers": {
"robloxstudio-mcp": {
"command": "cmd",
"args": ["/c", "npx", "-y", "robloxstudio-mcp@latest"]
}
}
}
What Can You Do?
Ask things like: "What's the structure of this game?", "Find scripts with deprecated APIs", "Create 50 test NPCs in a grid", "Optimize this movement code"
Inspector Edition (Read-Only)
robloxstudio-mcp-inspector
A lighter, read-only version that only exposes inspection tools. No writes, no script edits, no object creation/deletion. Ideal for safely browsing game structure, reviewing scripts, and debugging without risk of accidental changes.
21 read-only tools: get_file_tree, search_files, get_place_info, get_services, search_objects, get_instance_properties, get_instance_children, search_by_property, get_class_info, get_project_structure, mass_get_property, get_script_source, grep_scripts, get_attribute, get_attributes, get_tags, get_tagged, get_selection, start_playtest, stop_playtest, get_playtest_output
Setup - same plugin, just swap the package name:
Claude:
claude mcp add robloxstudio-inspector -- npx -y robloxstudio-mcp-inspector@latest
Codex:
codex mcp add robloxstudio-inspector -- npx -y robloxstudio-mcp-inspector@latest
Gemini:
gemini mcp add robloxstudio-inspector npx --trust -- -y robloxstudio-mcp-inspector@latest
Other MCP clients (Claude Desktop, Cursor, etc.)
{
"mcpServers": {
"robloxstudio-mcp-inspector": {
"command": "npx",
"args": ["-y", "robloxstudio-mcp-inspector@latest"]
}
}
}
Windows users: If you encounter issues, use cmd:
{
"mcpServers": {
"robloxstudio-mcp-inspector": {
"command": "cmd",
"args": ["/c", "npx", "-y", "robloxstudio-mcp-inspector@latest"]
}
}
}
**v2.4.0** - 39 tools, inspector edition, monorepo architecture
Report Issues | DevForum | MIT Licensed
Servidores relacionados
Scout Monitoring MCP
patrocinadorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
patrocinadorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Grantex MCP
13-tool MCP server for AI agent authorization. Manage agents, grants, tokens, and audit logs from Claude Desktop, Cursor, or Windsurf. Plus @grantex/mcp-auth for adding OAuth
Remote MCP Server (Authless)
An example remote MCP server deployable on Cloudflare Workers without authentication.
Atlas Docs
Access technical documentation for libraries and frameworks, formatted in clean markdown for LLM consumption.
StatsWR MCP Server
A template for deploying a remote MCP server on Cloudflare Workers without authentication.
Argo CD
Interact with Argo CD applications through natural language.
Image Generation
Generate images from text prompts using the Together AI API.
SumUp
Build card present and online payments solutions with SumUp.
Authless Remote MCP Server on Cloudflare
An example of a remote MCP server deployable on Cloudflare Workers without authentication.
Criage MCP Server
An MCP server for the Criage package manager, providing full client functionality via the MCP protocol.
Lean LSP
Interact with the Lean theorem prover via the Language Server Protocol (LSP), enabling LLM agents to understand, analyze, and modify Lean projects.