Gemini Desktop App to Support MCP, Image/Video Generation, and Camera Input
testingcatalog · x · 2026-08-03
Google is testing several major new features for the Gemini desktop app to bridge the gap with its web counterpart.
Key updates include:
- MCP Support: The connectors menu for Gemini Spark now includes an option to add custom MCP servers, bringing previously internal configurations into visible agent settings.
- Multimodal Generation: Dedicated tabs for image and video generation are being added to the app's navigation.
- Camera Attachment: A new camera option in the attachment menu allows users to capture photos and drop them directly into the prompt.
These features are currently in trusted-tester builds with no public rollout date announced yet.
More from coding & agent
- DeepSeek v4 Flash Paired with Hermes Agent Yields Best Output Files in Tests — Teknium · 2026-08-03
- NousResearch Co-founder Breaks Down the Evolution of Personal AI Agent Hermes — petergyang · 2026-08-03
- MiniMax H3 Text-to-Video ComfyUI Workflow Released — Fresh_Sun_1017 · 2026-08-03
- Vercel's Internal AI Agent Sees Exponential Growth in Daily Interactions and Token Use — cramforce · 2026-08-03
- Why Do Almost All AI-Generated Projects End Up Being Web Apps? — iamaliveix · 2026-08-03
- The Weird Feeling of Asking a Deterministic Code Model to 'Think Before Proceeding' — MickeySteamboat · 2026-08-03