Google has expanded the Managed Agents capability in its Gemini API, adding background execution, remote MCP server connections, custom function calling and network credential refresh.

The updates let developers run long-running agent tasks asynchronously rather than holding open an HTTP connection, with the API returning an interaction ID that can be polled or streamed later. Agents can now also connect directly to remote MCP servers to reach private databases or internal APIs from inside a secure sandbox, alongside built-in tools such as code execution and Google Search.

Custom function calling has been added so client-side business logic can run alongside server-side sandbox tools, with the API pausing interactions that require local execution. A network credential refresh feature allows developers to rotate expiring access tokens or API keys mid-session without losing the sandbox's existing filesystem state, installed packages or cloned repositories.

The changes were detailed by Philipp Schmid and Mariano Cocirio of Google DeepMind, who framed the release as a step towards agents that can work unattended on real infrastructure without tying up a live connection.

AI for Leaders: Governance, Risk & Why Strategy Must Come First
Is your organisation adopting AI without a defined strategy or governance? If so, you’re not alone — and the consequences range from data breaches to reputational damage to safeguarding failures. AI is a strategic risk, not a silver bullet, and definitely not a magic data fairy. Without clear ownership, rules, and accountability, AI can proliferate across your organisation in ways that cost more — in time, money, and trust — than not using it at all. Speakers: Craig Clark, Director at Clark & Company Information Governance Services, and Stewart Tinson, Project Director, AI-360. You’ll learn: Why “understand your why” must precede any AI rollout Which risks senior leaders most commonly overlook — from data leakage to safeguarding How to measure AI value through outcomes, not adoption metrics Why accountability for AI governance sits with the C-suite, not IT or compliance Key topics: AI strategy • Risk appetite • Data protection • Bias & fairness • Safeguarding • AI literacy • Governance models • Return on investment • Executive accountability • AI use case tiering For CISOs, CIOs, and senior leaders who need to govern AI responsibly — before it governs them.
BrightTALK
Share this post
The link has been copied!