Microsoft launches MXC, a cross-platform container sandbox for AI agents
Microsoft Execution Containers uses a unified JSON config and SDK to limit the files, networks and system resources an agent can access, with permissions enforced outside the agent; Copilot, Codex and Replit already support it.
Microsoft has launched a new container system for AI agents across Windows, Linux and macOS. It’s called Microsoft Execution Containers, or MXC, and it lets developers control which files, networks and system resources an agent can access. An agent can edit your project and run its tools while being blocked from personal files or changing configurations it only needs to read. These restrictions are enforced outside the agent’s control, so it can’t grant itself extra permissions. MXC uses platform-specific sandboxes, including Bubblewrap on Linux, through a unified JSON configuration and SDK. GitHub Copilot, OpenAI Codex, Replit and OpenClaw already support it, with Claude Code support planned. Source: https://blogs.windows.com/windowsdeveloper/2026/10/07/microsoft-execution-containers-policy-driven-containment-for-ai-agents/