Google's Deep Research lands in Gemini API with MCP and native charts
Google upgraded Deep Research in the Gemini API with MCP support, native chart generation, and a Max tier for heavy async tasks.
Google just upgraded Deep Research and launched Deep Research Max directly in the Gemini API — no Gemini consumer app, API-only.
Three headline additions: MCP (Model Context Protocol) support lets the agent connect to proprietary data sources via external tools; native chart and infographic generation renders visuals directly in HTML without third-party tooling; and a new quality split — the standard agent optimizes for speed, while Max mode runs longer, asynchronous deep dives with extra compute.
Both tiers also gain multimodal input (PDFs, CSVs, images, audio, video), collaborative planning (review and tweak the search plan before it runs), and real-time streaming of intermediate research steps.
Why it matters: autonomous, MCP-connected research agents in the API means developers can wire deep multi-source research directly into their own products — no UI required.
Sources
- 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. How it works.
Feed, daily deep-dive and bytes — readable offline, with push alerts for the topics you follow.