Google Deepmind adds background execution and MCP support to Gemini API managed agents

Google Deepmind has launched four new features for Managed Agents in the Gemini API, including background execution, remote MCP server support, custom function integration, and credential refresh capabilities. The updates enable developers to run agents asynchronously without open HTTP connections and connect to internal databases or APIs. All features are available through the Gemini Interactions API with code examples in JavaScript, Python, and cURL.

Google Deepmind adds background execution and MCP support to Gemini API managed agents Google Deepmind is adding four new features to Managed Agents in the Gemini API. Developers can now run agents asynchronously in the background using Background Execution https://ai.google.dev/gemini-api/docs/agents , with no open HTTP connection required. Remote MCP Model Context Protocol servers can also be connected directly to internal databases or APIs. Another addition lets developers use custom functions alongside the built-in sandbox tools. Finally, credentials like tokens can be refreshed https://ai.google.dev/gemini-api/docs/agent-environment refresh-credentials between interactions without losing the sandbox state. All features are available through the Gemini Interactions API. Code examples for JavaScript, Python, and cURL are in the documentation https://ai.google.dev/gemini-api/docs/managed-agents-quickstart . AI News Without the Hype – Curated by Humans Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section. Subscribe now Source: Google https://blog.google/innovation-and-ai/technology/developers-tools/expanding-managed-agents-gemini-api/