New Capabilities for Managed Agents: Background Execution, Remote MCP, and Skills Support
Managed agents now support long-running background execution, remote MCP server integration, and skills support, so you can build reliable, production-ready agents.
Today we're announcing new capabilities for Managed Agents in the Gemini API, including background execution, remote MCP server integration, and skills support. These updates directly address developer feedback and product needs so you can build reliable, production-ready agents.
With our managed agents, you call a single endpoint and The Agents Layer handles reasoning, code execution, package installation, file management, and web information inside an isolated cloud sandbox.
Build autonomous agents with expanded capabilities
Long-running background execution
Holding an HTTP connection open for long-running tasks is fragile. Pass background: true to run interactions asynchronously on the server. The API immediately returns a stream so you can track progress.
Remote MCP server integration
Instead of writing custom proxy middleware to access private databases or internal APIs, you can now connect managed agents directly to remote Model Context Protocol (MCP) servers.
You can mix and match remote tools with built-in sandbox capabilities. Set up an MCP server in a single step to let the agent communicate with your endpoints from its secure sandbox, and follow best practices as you extend your agent with external tools and APIs.
Get started with our managed agents
These updates turn managed agents into asynchronous workers that operate inside real development environments without blocking your application.