Google Expands Gemini API Managed Agents With Background Execution, Remote MCP Support, and Mid-Session Credential Refresh

Google expands its Gemini API Managed Agents with powerful new features including background execution for long-running tasks, remote MCP server support, custom function calling, and mid-session credential refresh that preserves sandbox state — making AI agents significantly more reliable and flexible for production use.

• Google is expanding Managed Agents in the Gemini API with new capabilities including background execution, remote MCP server integration, custom function calling, and network credential refresh.
• Developers can now run long-running agent tasks asynchronously using background execution, connect agents directly to remote Model Context Protocol servers, and mix custom functions with built-in sandbox tools for flexible local and server-side execution.
• The credential refresh feature allows access tokens and API keys to be updated mid-session without losing sandbox state, including filesystem data, installed packages, and cloned repositories, making agents more reliable for production use.