Running AI Agents in Secure Sandboxes with E2B & Docker MCP | Docker’s AI Guide to the Galaxy

In this episode of AI Guide to the Galaxy, Docker’s Oleg Šelajev sits down with Jonas Scholz from E2B at the Docker Captain Summit to explore how E2B and Docker are partnering to make it easier and safer to run AI agents in isolated environments. E2B provides open-source infrastructure for AI sandboxes, giving developers full, cloud-based Linux VMs where AI agents can run securely. Combined with Docker’s MCP Catalog, this integration lets you spin up sandboxes with pre-configured, trusted MCP servers that are ready to use out of the box. Watch as Oleg and Jonas walk through: -- What E2B sandboxes are and how they work -- How Docker’s MCP Toolkit and Gateway integrate with E2B -- A live demo of running Claude inside a sandbox using MCP servers -- How developers can configure, scale, and automate AI sandboxes for coding agents and research assistants -- Tips on using Docker Hub, OAuth, and MCP remote servers If you’ve ever wondered how to run AI workloads safely at scale, or want to explore how Docker and E2B simplify agent infrastructure, this episode is for you. 🔥 Want More Docker Content? If you found this demo exciting, hit that like button and subscribe for more! We’ve got even more Docker demos coming your way in this ongoing series showcasing new tools, integrations, and powerful workflows to level up your projects. Stay tuned! Where to find Docker: Docker: https://www.docker.com/ LinkedIn:   / docker   Bluesky: https://bsky.app/profile/docker.com X: @docker Instagram: @dockerinc #Docker #E2B #AI #AIAgents #AIGuideToTheGalaxy #DevTools #DockerCaptains #OpenSource #MCP #CloudComputing #SandboxSecurity #ClaudeAI #DeveloperCommunity #DockerMCP #AIDevelopment