Google Deepmind 为 Gemini API 托管智能体增加后台执行与 MCP 支持

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

AI 导读

Google Deepmind 为 Gemini API 中的 Managed Agents 新增四项功能：Background Execution 支持异步后台运行，无需保持 HTTP 连接；可连接远程 MCP 服务器到内部数据库或 API；允许在内置沙箱工具旁使用自定义函数；交互间可刷新令牌等凭据而不丢失沙箱状态。所有功能通过 Gemini Interactions API 提供，文档包含 JavaScript、Python 和 cURL 代码示例。

正文 · 原文

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, 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 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.