Google's Deep Research hits the Gemini API with MCP & native charts
Deep Research and its Max variant are now API-accessible with MCP support, proprietary data grounding, and built-in chart generation.
Google has pushed Deep Research and Deep Research Max into the Gemini API — both built on Gemini 2.5 Pro. The standard tier optimizes for speed and real-time use; the Max variant trades latency for thoroughness, designed for async background research tasks that need maximum depth.
The headline upgrade is MCP (Model Context Protocol) support, letting developers wire Deep Research into their own proprietary data sources — financial feeds, internal docs, specialized databases — while keeping Google Search grounding active in the same request. The agents can now also generate native charts and infographics inline, not just text summaries.
Notably, this is API-only. None of it is live in the Gemini consumer app yet — it's squarely aimed at developers building research-heavy products via the Interactions API.
Why it matters: Deep Research as a callable agent changes the game for dev teams — you get a full web + proprietary data research workflow in a single API call, with structured output and visuals included.
Sources
Independent coverage
- Build with Gemini Deep Research blog.google
- Google launches Deep Research and Deep Research Max agents the-decoder.com
Written by an AI pipeline from the sources above. Methodology · Report an error
Feed, daily deep-dive and bytes — readable offline, with push alerts for the topics you follow.