Expanding Managed Agents in Gemini API: background tasks, remote MCP and more
Source: Google AI
Intel Summary
Google has announced updates to Managed Agents within the Gemini API, introducing support for asynchronous background tasks and remote Model Context Protocol (MCP) integrations. According to Google, these enhancements are designed to help software developers construct more reliable, production-ready autonomous agents. The integration of remote MCP standardises external tool connectivity, while background execution allows agents to manage long-running workflows without maintaining persistent active client connections.
Why It Matters
Adopting standard protocols like MCP across major commercial APIs reduces vendor lock-in and simplifies enterprise integration with diverse external data sources and execution environments. By handling long-running background tasks natively at the managed agent layer, developers can implement multi-step autonomous workflows without building custom scheduling infrastructure, accelerating the deployment of complex generative agent systems.
Part of an ongoing development
Primary sourceGoogle updates Managed Agents in Gemini API with background tasks and remote MCP support
Google has announced updates to Managed Agents within the Gemini API, introducing support for asynchronous background tasks and remote Model Context Protocol (MCP) integrations. The integration of remote MCP standardises external tool connectivity, while background execution allows agents to manage long-running workflows without maintaining persistent active client connections. Claims are as reported; this summary makes no determination about accuracy or significance.
- Confidence
- Moderate confidence
- Corroboration
- Limited corroboration
Organizations & Entities
Topics
Related Intelligence
- DevelopmentNewAlso involving Model Context Protocol
Anthropic introduced Model Hardware Standard
Anthropic has introduced the Model Hardware Standard, a new specification designed to enable artificial intelligence agents to interface with and control physical machinery. The initiative marks Anthropic's expansion beyond software-confined applications into cyber-physical automation, industrial robotics, and hardware control. Claims are as reported; this summary makes no determination about accuracy or significance.
5 independent sources - DevelopmentNewAlso involving Google
Google DeepMind expands Co-Scientist to automate lab experiments and paper writing
Google DeepMind has expanded its Co-Scientist system from hypothesis generation into an integrated laboratory research platform. Powered by a Gemini-based multi-agent architecture, the system plans scientific experiments, interfaces directly with laboratory equipment to execute them, and writes corresponding scientific papers. Claims are as reported; this summary makes no determination about accuracy or significance.
1 reporting source - DevelopmentNewAlso involving Google Gemini
Google DeepMind introduced Co-Scientist
Google DeepMind has introduced Co-Scientist, a multi-agent artificial intelligence system designed to assist scientists and accelerate scientific discoveries. Built on Google Gemini models, the system employs collaborative agent architectures to support scientific workflows, hypothesis formulation, and research analysis. Claims are as reported; this summary makes no determination about accuracy or significance.
- DevelopmentDeveloping
OpenAI launches Astra model
TechCrunch reports that OpenAI has launched Astra, a new model designed for computer and browser use. Claims are as reported; this summary makes no determination about accuracy or significance.
7 independent sources