Roblox AI Agents
Enables AI agents to build and edit Roblox Studio places by inspecting, generating terrain, geometry, and code, with validation and iteration.
README
Roblox AI Agents
Give Claude, Codex, Cursor, Gemini CLI, and other coding agents a real bridge into Roblox Studio.
Roblox AI Agents is a local MCP server plus a Roblox Studio plugin. Your agent can inspect the open place, draft a SceneSpec, generate terrain, create map geometry, write safe Luau, mirror code into Rojo, validate the result, and iterate inside Studio instead of pretending a .rbxl file is enough.
Prompt -> SceneSpec -> dry run -> apply in Studio -> validate -> playtest
Install for agents
Claude Code:
/plugin marketplace add ShiroKSH/roblox-ai-agents
/plugin install roblox-ai-agents@roblox-ai-agents
Codex, Cursor, Copilot, Gemini CLI, and other Agent Skills hosts:
npx skills add ShiroKSH/roblox-ai-agents -g
-g installs the skill globally for your user. Drop it to install into the current project.
The skill teaches agents the Roblox build workflow. The local bridge still needs to run from this repo:
git clone https://github.com/ShiroKSH/roblox-ai-agents.git
cd roblox-ai-agents
npm install
npm run build
Install the Studio plugin
Requirements:
- Node.js 20+
- Roblox Studio
- Rojo, for plugin builds
Build the plugin:
npm run build:plugin
Copy dist/RobloxAIAgents.rbxm into your Roblox local plugins folder:
- Windows:
%LOCALAPPDATA%\Roblox\Plugins - macOS:
~/Documents/Roblox/Plugins
Manual fallback: create a local Studio plugin from plugin/src/init.lua and add the files in plugin/src/Bridge as child ModuleScripts under a Bridge folder.
Start the bridge
Create a local token:
cp .env.example .env
Edit .env and set ROBLOX_AI_AGENTS_TOKEN to a random local value. Do not use Roblox credentials.
Start the MCP server:
npm run build
node packages/mcp-server/dist/index.js
If no token is set, the server prints a one-time token to stderr. Paste it into the Studio plugin.
Connect Codex
codex mcp add roblox-studio -- node packages/mcp-server/dist/index.js
Example config.toml:
[mcp_servers.roblox-studio]
command = "node"
args = ["packages/mcp-server/dist/index.js"]
startup_timeout_sec = 15
tool_timeout_sec = 120
default_tools_approval_mode = "prompt"
Connect Studio
- Open Roblox Studio.
- Enable HTTP requests for the place.
- Open the
Roblox AI Agentsplugin panel. - Use host
127.0.0.1, port3765, and the same token as the MCP server. - Click
Connect.
Verify from your agent:
studio_ping
The response should include plugin version, place name, place id, and Connected.
What it can build
- Blockouts, obbies, arenas, cabins, streets, training maps, and playable grayboxes.
- Terrain and pathing through Studio APIs.
- Doors, buttons, lifts, teleporters, checkpoints, and scoped runtime scripts.
- Batched Studio edits with Undo support.
- Rojo artifacts under
generated/rojo/<mapName>whencodegen.targetisrojoorboth. - Validation passes for safe roots, spawn points, anchoring, terrain penetration, stair clearance, doorways, and common map-readiness issues.
Evolution sample
These are cropped Roblox viewport shots from the local build process, with desktop UI, downloads, chats, tokens, and personal data removed.
| V1 first pass | V4 roof pass |
|---|---|
![]() |
![]() |
| V4 balcony detail | V4 window detail |
|---|---|
![]() |
![]() |
| Latest playtest frame | Latest station detail |
|---|---|
![]() |
![]() |
Build workflow
- Convert the request into a SceneSpec. Set
rootPathtoWorkspace/MapDrafts. - Use named levels, areas, folders, and models. Keep instance names unique.
- Use
functionalObjectsfor doors, buttons, lifts, teleporters, and checkpoints. - Set
codegen.targettobothwhen Luau should be written into Studio and mirrored into Rojo. - Run
map_apply_scene_specwithdryRun=true. - Review target root, object count, touched services, and risks.
- Run
map_apply_scene_specwithdryRun=false. - Run
map_validatewithstrictGeometry=true. - Run
map_readiness_checkwith the matching profile when the map is meant to be playable. - Playtest in Studio and check plugin output before calling the map ready.
Use examples/simple-obby.scene.json for a minimal SceneSpec. The map root will be Workspace/MapDrafts/<mapName>_<timestamp>. A filesystem manifest is written under logs/manifests/.../map_manifest.json, and a SceneManifest StringValue is placed under the map root.
For in-place repair, use studio_patch_instances instead of one-off apply scripts. For inspection, move the Studio viewport with studio_focus_instance or studio_set_camera, then use studio_visual_probe to raycast what the camera sees.
Safety defaults
- Localhost only.
- Shared token required.
- Dangerous Luau disabled by default.
- Deletes require
confirmToken. - New build writes stay under
Workspace/MapDrafts. - Legacy
Workspace/AI_Generatedpaths are for migration only. - Command logs redact tokens, source, and code.
- Roblox credentials and
.ROBLOSECURITYare never needed.
Final result
The point is not a text-only plan. The agent can keep pushing real Studio geometry until the place looks like an actual Roblox build:

Development
npm install
npm run build
npm test
npm run validate:skill
More detail:
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。




