On July 7, 2026, Google added four capabilities to Managed Agents in the Gemini API: background execution for long-running tasks, direct integration with remote Model Context Protocol servers, custom function calling alongside built-in sandbox tools, and a mechanism to refresh network credentials mid-session without losing an agent's existing state. The update was published on Google's official developer blog and authored by Philipp Schmid and Mariano Cocirio of Google DeepMind. The most structurally significant addition is background execution, where setting `background: true` on an interaction tells the API to run the task asynchronously on Google's servers rather than over a live connection, returning an interaction ID immediately for polling or reconnection. Remote MCP server integration lets a managed agent connect directly to a remote MCP server at interaction time, alongside built-in sandbox tools such as Google Search or code execution. Google introduced the Managed Agents API at Google I/O 2026 on May 19, 2026, alongside the Gemini 3.5 model series and Antigravity 2.0.