Google's Gemini Spark adds third-party app integrations including Anthropic's MCP and real-time event tracking
Google is rolling out third-party app support for Gemini Spark, its 24/7 personal agent available to Google AI Ultra subscribers. The update includes Model Context Protocol (MCP) integration and real-time event tracking capabilities.
Google's Gemini Spark adds third-party app integrations including Anthropic's MCP and real-time event tracking
Google is rolling out third-party app support for Gemini Spark, its 24/7 personal agent available to Google AI Ultra subscribers. The update includes Model Context Protocol (MCP) integration and real-time event tracking capabilities.
Third-party integrations
Gemini Spark now supports integrations with Canva, Dropbox, Instacart, OpenTable, and Zillow Rentals, according to Google. Users can design custom flyers, access and share files, reserve restaurant tables, order groceries, or schedule apartment tours through the agent.
First-party integrations have expanded to include Google Keep and Tasks. Spark can scan notes in Keep and convert them into actionable items in Tasks.
The third-party app support is rolling out to Gemini Spark on web and mobile over the next week, with macOS support coming in the "coming weeks," according to Google.
Model Context Protocol support
Google has added support for the Model Context Protocol (MCP), originally developed by Anthropic. Users can enter custom app links at gemini.google.com/apps to enable MCP integrations.
MCP provides a standardized way for AI assistants to connect with external data sources and tools. The protocol's inclusion allows developers to build custom integrations without platform-specific implementations.
Real-time event tracking
Gemini Spark now monitors topics and events in real time. The agent can track sports matches, stock price thresholds, blogs, news sites, social media, finance data, shopping, and weather updates.
According to Google, users can configure Spark to deliver match highlights and analysis after games end, or receive financial reports when stocks hit specific price points. The system monitors configured sources continuously without requiring manual refreshes.
Availability
All features are available exclusively to Google AI Ultra subscribers. Pricing for Google AI Ultra has not been disclosed. The updates follow Google's recent launch of Gemini Spark macOS app support.
What this means
Google's addition of MCP support signals cross-platform standardization in AI agent tooling, particularly as Anthropic's protocol gains adoption. The real-time monitoring capabilities position Gemini Spark as a proactive assistant rather than reactive chatbot, competing directly with notification systems and RSS readers. However, the restriction to Google AI Ultra subscribers limits the feature set to paying users, and Google has not disclosed subscriber numbers or pricing tiers for comparison with competitors like Claude or ChatGPT Plus.
Related Articles
Google to Let Users Remove Visible AI Watermarks From Nano Banana, Omni, Lyria Content
Google VP Josh Woodward announced a new toggle that lets users remove visible sparkle-icon watermarks from AI-generated content made with Nano Banana, Omni, and Lyria. The invisible SynthID watermark and C2PA metadata will remain unaffected, and the toggle won't roll out in the EU or South Korea where visible labeling is legally required.
Google Lets Users Turn Off Visible Watermarks on Nano Banana, Omni, and Lyria Outputs
Google announced users can now toggle off visible watermarks on AI-generated images, video, and songs from its Nano Banana, Omni, and Lyria models. Invisible SynthID watermarks and C2PA metadata remain in place for transparency.
Anthropic to Launch Watermark Detection API for Identifying AI-Generated Claude Text
Anthropic is rolling out a watermark detection API that lets third-party developers check whether text was generated by Claude. The move stems from EU AI Act compliance requirements and uses a variant of Google DeepMind's SynthID Text method.
ChatGPT Paid Users Can Now Edit Google Drive Files Without Leaving the Chat
OpenAI has expanded ChatGPT's Google Drive integration, allowing paid subscribers to add Drive files to their ChatGPT Library and edit them directly inside the chat interface. The edits apply to the actual file in Drive, not a copied version.
Comments
Loading...