Google Deepmind adds background execution and MCP support to Gemini API managed agents
Google's Gemini API agents just got async execution and MCP support—now developers can build stateful, long-running AI workflows without the complexity.
Why it matters
Google is expanding the Gemini API's managed agents product with infrastructure features (async background execution, MCP server integration, credential refresh) that reduce friction for developers building production AI applications. This positions Gemini agents as a viable alternative to custom agent frameworks and signals Google's competitive push in the agent-as-a-service market.
The key facts
6 to knowFour new features added to Managed Agents in Gemini API
Asynchronous background execution capability
Direct MCP (Model Context Protocol) server integration
Custom function support alongside sandbox tools
Stateful credential refresh without state loss
Published July 2026 — recent product iteration
Go to the source
The Decoderthe-decoder.com
Publisher excerpt: Google Deepmind is adding four new features to Managed Agents in the Gemini API. Agents can now run asynchronously in the background, connect directly to remote MCP servers, use custom functions alongside sandbox tools, and refresh credentials without losing state.