About Full capable coding agent MCP server
Runbox MCP provides a remote coding sandbox for AI agents to build, test, edit, and publish websites. It combines command execution and a live editor with public URLs for sharing deployed sites.
Key features
- 01Build and edit code in a remote sandbox
- 02Run commands to test and debug code
- 03Edit source in a live editor
- 04Support multiple HTML, JS, and CSS files
- 05Publish sites to public URLs
Use cases
- 01Build and publish a website from AI-generated code
- 02Test a website through a shareable live URL
MCP support
It exposes remote coding, command execution, editing, and website publishing capabilities to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
7Saved tool list · updated 3w ago
This tool takes no parameters.
Details
From the project READMERunbox Website Builder MCP
Runbox MCP provides remote coding environment for AI and agents. It can publish your AI-written website code as real world URL domain. Deploy your AI generated code as a real website running in remote server.
Capability:
- Publish static html, js, css files as public website URL to share
- Live code editor to edit source code and update website content
- Build website, read/write code in remote code sandbox
- Execute commands safely in remote sandbox to test the code and fix bugs
- Serve code as real website URL to test demo
demo video: https://www.youtube.com/watch?v=ONvT516jLBo
Install
{
"mcpServers": {
"runbox-website-publisher": {
"command": "npx",
"args": ["-y", "code-sandbox-mcp@latest"]
}
}
}
Features
From chat to publish website live
Just ask Claude: "Create a xyz website and publish to runbox" and you will get a URL hosting your website like https://runbox.ai/site/VnIdYXn5bIBGyv9X/
Live code editor
Easily view and edit Claude generated code in a live editor
Multi files supprot
Support multiple html, js, css and other files
Dev
server side code: https://github.com/11cafe/code-sandbox-server
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.