I tried using Gemini for work, but it falls apart the moment I leave Google's ecosystem

Published Sep 11, 2026, 11:15 AM EDT I've been writing about Android since 2011, with a focus on device reviews, Samsung and Google Pixel hardware, and the latest happenings in the ecosystem. In my entire writing career, I've reviewed more than 75 Android phones. Carrying both a Samsung or Pixel flagship and an iPhone as a daily driver provides me with deep insight into how Android works and how it compares to iOS. I have been writing for Android Police since 2021, covering news, how-tos, and features. You can find my previous work on Neowin, AndroidBeat, Times of India, iPhoneHacks, MySmartPrice, and MakeUseOf. When not working, I tend to mindlessly scroll through X, play with new AI models, or go on long road trips. You can reach out to me on X or drop a mail at rajesh@androidpolice.com. I pay for ChatGPT, Claude, and Gemini, but I don't use any of them for coding. Instead, I rely on AI assistants to speed up my everyday work, from research to managing projects. Gemini should have a big advantage over others here. All my data lives in Google Drive, Gmail, and other Google services. Plus, Gemini is deeply integrated into Google's ecosystem. But that strength is also Gemini's biggest weakness when I want to get work done. Gemini works best within Google's ecosystem Google gives Gemini an edge In the last year or so, Google has integrated Gemini across its products and services. I'm heavily invested in Google's ecosystem, which has made Gemini my go-to AI assistant when working on projects. I use it to find buried information in my Google Drive files, summarize long documents, surface important emails, and organize messy Google Sheets. Google has the context, which I can pass on to Gemini thanks to the deep integration. Otherwise, I would have to manually feed content to an AI assistant to get it to work. Gemini Spark, Google's AI agent, has been another boon for my workflow. I use it to finalize hotel and holiday bookings, draft replies to important emails by pulling relevant context and information from multiple sources, and more. For me, this integration with Google's ecosystem is Gemini's biggest advantage over other AI assistants. I don't care if it tops coding tests or leads another AI benchmark. What matters more is how easily it fits into my existing workflow and helps me get things done. Gemini's advantage disappears outside Google Outside Google, things fall apart The problem is that my work doesn't stop at Gmail and Drive. I use third-party tools and apps for project management, research, CRM, communication, and more. Gemini doesn't work with them. You can connect Gemini with some third-party services, but that list is limited. If you are just starting to use AI assistants, this may not bother you. But as someone who is using AI to get work done every day, this is a big problem. I use Zoho Bigin — a CRM tool — to manage my business's sales pipeline. Through MCP (Model Context Protocol), I have connected Bigin to ChatGPT, letting me pull and work with its data in a conversation. For example, I frequently ask ChatGPT to check a lead's status in Bigin, analyze how it moved through the sales pipeline, and more. I don't have to export the data, upload screenshots, or explain the context every time. ChatGPT uses MCP to communicate with Bigin and get the information it needs. Likewise, during this workflow, I may come across tasks that need immediate attention. In such cases, I ask ChatGPT to add the relevant tasks to Todoist, my to-do app of choice. The solution already exists Google already knows where this is heading When you connect AI assistants to the services you use through MCP, it changes the way you work. This is where Google's approach with Gemini feels unnecessarily restrictive. Instead of supporting MCP more broadly — a solution that exists and is adopted by ChatGPT and Claude — Google is adding support for third-party integrations individually. What's even more frustrating is that Google supports MCP. Gemini Spark lets you connect third-party apps using their MCP server URLs, while Google offers MCP support across its enterprise and developer-focused products. This is different from having my MCP-connected tools available whenever I start a regular conversation with Gemini. All this makes it clear that Google knows the importance of MCP and that an AI agent should communicate with external tools and data. Yet it has been agonizingly slow to embrace MCP. Adopting MCP does not mean that Google needs to abandon its existing Connected Apps approach. Google currently uses the latter to let Gemini talk with third-party services such as Dropbox, Spotify, and GitHub. However, the problem with this implementation is that Google can't build and maintain Gemini integration for every CRM, to-do list, or productivity app. That's why it needs MCP. Gemini needs to break out of Google's walls I don't need Gemini to become better at coding or score higher on benchmarks. Before all that, I need it to do work with the tools I use every day. That's what makes Google's slow adoption of MCP and Gemini's limited support for third-party apps frustrating. Gemini has an advantage over other AI assistants: its deep integration with Google's ecosystem. Adding MCP support will make Gemini irreplaceable for my workflow. Gemini has access to more of my work and personal data than any other AI assistant. It needs to let it do more with all that context. And for that, Gemini must break free from Google's walls.