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.

With the growing Serverless workloads, managing and maintaining them is best recommended with Infrastructure as Code (IaC). While this holds the complete infrastructure and its configurations, we could have events from one service destined to another via configuration. When building these configurations, we could also reduce the application code making it more maintainable and scalable. In this session, Jones walked us through a fully end-to-end solution built with Amazon EventBridge and AWS Step Functions with SDK integrations which have helped him to improvise the application with just IaC and very minimal application code.

Tired of rebuilding your stack from scratch every time you run tests or restart your dev environment? In this episode, we dive into Cloud Pods, LocalStack’s powerful state management feature. You’ll learn how to snapshot your entire LocalStack environment (services, resources, data), restore that exact state across machines, teams, or CI runs, speed up test cycles and workflows, and use Cloud Pods to make testing in CI/CD faster and more reliable. Cloud Pods let you freeze your infrastructure in time. Perfect for repeatable tests, isolated dev environments, or onboarding new teammates.

dbt (Data Build Tool) helps data engineers manage data transformations using modular SQL and brings version control, testing, and documentation to their transformation logic. However, running dbt against production data warehouses like Snowflake can be slow, expensive, and risky. This session introduces a new way to develop and test dbt workflows locally using the Snowflake emulator in LocalStack. You'll learn how to set up a local dbt environment, configure dbt to connect to the Snowflake emulator, run and validate dbt models locally without using a real Snowflake account, and iterate quickly on transformations before pushing them to production. Through a hands-on factory app example, we’ll walk through how to use the Snowflake emulator to run dbt models on your laptop, helping you test logic, catch issues early, and reduce cloud costs.