What if your AI coding assistant could not only write infrastructure code, but also deploy it, test it, and fix issues automatically — all on your local machine? That's exactly what the LocalStack MCP Server makes possible. In this session, we'll introduce the LocalStack Model Context Protocol (MCP) Server, a new tool that lets AI agents manage your entire local cloud development lifecycle through a conversational interface. You'll learn what MCP is and why it's a game-changer for AI-assisted development, how the LocalStack MCP Server turns manual cloud tasks into automated workflows, how to set up and configure the server with your favorite AI editor (Cursor, VS Code, etc.), and real-world demos: deploying CDK apps, analyzing logs, running chaos tests, managing state with Cloud Pods, and more. Through hands-on examples, we'll walk through a complete workflow where an AI agent deploys a serverless application, verifies resources, troubleshoots issues, and tests resilience, all without leaving the conversation. If you've ever wished your AI assistant could do more than just generate code, this talk will show you what's possible when agents can actually manage your local cloud environment.

LocalStack's cloud emulator lets you run Amazon Elastic Container Service (ECS) clusters and tasks on your local computer. It's sometimes useful to mount code from the host filesystem directly into the ECS container. This helps quickly test changes without needing to rebuild and redeploy the ECS Task's Docker image each time. This video explains how to use code mounting with the ECS bind mounts feature.

We’re partnering with gdotv to simplify development with our Amazon Neptune cloud emulator component. You can now easily query, visualise and model your graph data either interactively or using the Gremlin querying language with G.V() - Gremlin IDE. With G.V(), you can considerably enhance your graph database development experience whilst gaining access to a powerful reporting and visualisation toolset for your production data. With LocalStack’s core cloud emulator, parity is ensured between a local Neptune instance and AWS’s own, meaning Gremlin queries in your development environment will behave identically on Amazon Neptune. In this video we demonstrate how to use G.V() with LocalStack Neptune.

Debugging serverless functions has always been challenging, often requiring repeated invocations, extensive log tracing, and cloud deployments to diagnose an issue. The new Lambda Debug Mode in LocalStack changes this by allowing developers to debug AWS Lambda functions directly in their IDE, with breakpoints, variable inspection, and step-through execution, without leaving their local environment. In this presentation, Marco Edoardo Palma provides a hands-on demo of Lambda Debug Mode—from debugging standalone functions to handling multi-function workflows. Learn how this developer-first approach makes debugging serverless applications faster, smoother, and more intuitive.