Gemini API gains asynchronous functions and remote tools
Google has updated the Gemini API for agents with asynchronous execution and support for remote Model Context Protocol (MCP) servers to facilitate the development of stable AI agents.
What happened?
On 9 July 2026, Google launched new features in its Managed Agents service within the Gemini API. The update includes asynchronous execution for long-running background processes and integrated remote Model Context Protocol (MCP) servers. According to Google, the aim is to solve challenges associated with maintaining open HTTP connections for extended processes.
Key facts
| Uppdateringsdatum | 9 juli 2026 |
|---|---|
| Tjänst | Gemini API, Managed Agents |
| Nya funktioner | Asynkron exekvering, Fjärr-MCP-stöd |
”Google has updated its Managed Agents service within the Gemini API, adding support for long-running background tasks and integration with remote Model Context Protocol (MCP) servers.”
”Developers can now initiate an asynchronous task by passing a`background: true` parameter in their API call. The API returns an ID for the process, allowing the client application to poll for status or reconnect later while the agent completes its work on Google's servers.”
”The second key addition is native support for remote MCP servers. MCP is an open specification for standardizing how AI systems connect to external tools and data sources. By allowing managed agents to connect directly to a remote MCP endpoint, Google aims to provide a single, se”
Why it matters
These additions address critical issues for developers building AI agents in production environments. Asynchronous execution eliminates the need for complex proxy solutions for long processes, while MCP support simplifies secure integration with external tools and data sources. This improves both the efficiency and security of agent development.
Who is affected?
Developers using the Gemini API to build AI agents are the primary recipients. Companies implementing AI solutions will also benefit from a more robust and secure infrastructure for their agents. End users may be indirectly affected through more reliable AI services.
What else you should know
The features are designed to replace proprietary middleware previously required by developers. MCP is an open specification for standardising connections between AI systems and external resources.
Quick answers about this story
Vad har hänt?
När hände det?
Varför spelar det roll?
The link opens in a new window and leads to the publisher's own site.
Källan har spårats automatiskt från utgivaren via Aheadlines signalkedja.
AI-verktyg i artikeln
Topics
Get similar news straight to your inbox
The reader's room
Send in a question or an addition. The newsroom reads everything before it's published and replies when relevant. No AI-generated text – just people.
Sign in to submit a comment or question.
Read the article through your role
- Assess technical risk: model choice, vendor lock-in, data flow and running cost.
- Update the architecture doc if new APIs or regulations touch production.
- Ensure observability + rollback plan before rolling out to production.
Generated angle — not editorial analysis of "Gemini API gains asynchronous functions and remote tools"