Google launches Connected Apps Platform to bring third-party apps into Gemini and Search
Google announced the Connected Apps Platform, a unified route for developers to bring their apps into Gemini and Search. More than 50 third-party Connected Apps already exist in the Gemini app, and a Calm integration is due in the coming weeks.
Google on October 28 announced the Connected Apps Platform, which it describes as a "unified way for more app developers to bring their capabilities directly into Gemini and Search." Until now, building a Connected App required working closely with Google. The platform opens that process to more developers, according to 9to5Google.
What exists today
Third-party Connected Apps in the Gemini app already cover Adobe, Dropbox, Instacart, OpenTable, Ticketmaster and other services, now numbering over 50. Google also announced a Calm integration that will be available in the coming weeks.
These @-integrations sit alongside first-party offerings including Google Workspace, Photos and YouTube.
How developers build Connected Apps
Google bills the platform as a way to "build once and reach high-intent users." The requirements and workflow are as follows:
- Technical requirement: a cloud-hosted MCP server, or an Android MCP using the AppFunctions APIs.
- Process: developers register, test and submit their Connected Apps through the new Google Connected Console.
- Console features: the website lets developers track traffic, latency and error rates, and control brand identity.
- Distribution choice: developers can "choose whether [their app] will go live in Search, the Gemini app, or both."
Search availability
Google will soon make existing Connected Apps available in Search. A date for the Search rollout was not given.
Access and timing
Developers can sign up for the preview at developers.google.com/connected-apps. Google is opening access in phases over the coming months. Pricing, revenue terms and any fees for developers are not yet disclosed.
The Gemini app also gained a new Customize page as part of its recent redesign.
What this means
The platform changes how third-party apps reach Gemini: from a process that required close work with Google to a self-service route built on MCP servers and Android AppFunctions. Using MCP as the entry point means developers with an existing cloud-hosted MCP server have a defined path to submission, and Android developers have a separate path through AppFunctions.
The per-surface choice between Search, the Gemini app or both gives developers control over where their app appears. The Connected Console's traffic, latency and error-rate reporting gives them operational visibility after launch. Because access opens in phases over the coming months, developers should expect to join a waitlist-style preview rather than publish immediately.
Related Articles
Google's Gemini 4 Carbon ranks #1 on Artificial Analysis Intelligence Index at 59, opens first to cyber defenders
Google announced Gemini 4 Carbon, which it says ranks #1 on v5.0 of the Artificial Analysis Intelligence Index with a score of 59. Access begins this week with a subset of cyber defenders through the Fairwind Program, at a stated price of $2 per million input tokens and $10 per million output tokens.
Google opens Android Studio to more than 40 third-party coding agents with Bring Your Own Agent
Google is opening Android Studio to more than 40 external coding agents, including Anthropic's Claude Agent and OpenAI's Codex, through a new Bring Your Own Agent feature in Android Studio Rabbit 2. At the Android Dev Summit, it also announced an alpha Agentic API powered by Gemini Nano 4, a beta AppFunctions API, and the $1,099 XREAL AURA smart glasses.
Google launches Genie 4 world model with audio and two-minute interactive sessions, powered by Gemini 3.8 Flash
Google announced Genie 4, a world model for generating interactive AI experiences that run about two minutes, up from one minute for Genie 3. It adds audio generation, real-time natural language updates and Gemini 3.8 Flash for its simulations. It launches as a research preview for trusted testers.
Apple adds beta AI assistant built on Apple and OpenAI models to Keynote, Pages and Numbers, with MCP support
Apple is adding a beta AI assistant, built on models from Apple and OpenAI, to Keynote, Pages and Numbers. The three apps also now support the Model Context Protocol on macOS 27 or later, so third-party AI agents can plug in. Logic Pro, Pixelmator Pro and Final Cut Pro get updates as well.
Comments
Loading...