Google DeepMind launches Deep Research and Deep Research Max with MCP support
Google DeepMind releases two autonomous research agents via the Gemini API, with MCP support for custom data connections.
Google DeepMind has launched two autonomous research agents — Deep Research and Deep Research Max — powered by Gemini 3.1 Pro and available to developers through the Gemini API.
Both agents can navigate the open web alongside custom data sources, including internal documents and specialized financial information, generating fully cited, professional-grade reports. Deep Research adds arbitrary MCP support, allowing secure connections to first- and third-party data without custom integration work. It is also the first Google research agent to natively produce presentation-ready visuals. The two tiers serve different use cases: Deep Research is optimized for speed and interactive applications, while Deep Research Max takes additional time to search and reason, targeting exhaustive background research tasks. The announcement, made by @GoogleDeepMind on X, positions the agents as composable components for enterprise pipelines — developers building on Gemini can route proprietary data sources through MCP rather than building bespoke connectors, which lowers the integration barrier for deploying deep research capabilities inside existing products.