What happens when an AI has access to a Node.js environment? Spoiler: wild things

Give an AI access to a real Node.js runtime, and things start to get interesting. It can run code, install packages, generate files, and even launch servers on the fly. In this talk, you will see how I built a Node.js Sandbox server powered by the Model Context Protocol (MCP), an open standard that connects AI to real tools and data in a safe, controlled way.

We will walk through how the sandbox works: starting fresh Docker containers, installing npm packages on the fly, executing JavaScript, and sending back logs or files. Everything happens through simple MCP messages, allowing the AI to interact with your system just like a developer would, only faster.

You will see how this unlocks powerful use cases like generating charts with Chart.js, summarizing long articles from the web, creating and testing QR codes, scraping and saving content, generating PDFs and fake CSV data, or even spinning up mock APIs in seconds. By the end, you will know how to build your own MCP server and give your AI the keys to a real coding playground.