For those of you wondering how to use MCP this was in my business news feed today. These are MCP connections.
Google's AI-fueled travel search engine sends online travel stocks into the red Nov. 17, 2025 1:54 PM ETAlphabet Inc. (GOOG) Stock, EXPE Stock, BKNG Stock, GOOGL StockMAR, CHH, LYV, TRIP, STUBBy: Amy Thielen, SA News Editor Google’s (GOOG) (GOOGL) new AI search tool to build a comprehensive travel itinerary is weighing on travel-related stocks with shares of Expedia (EXPE), Booking Holdings (BKNG), and Trip.com (TRIP) falling further into the red. On Monday, Google (GOOG) (GOOGL) launched a new AI-powered search tool to find flights and hotels and customize a travel itinerary to help travelers find the best deals. This includes an expanded Flight Deals search engine within Google Flights, designed for travelers who want to find last minute deals and affordable destinations. Travelers can share their potential travel plans with Google in AI mode, select "Create with Canvas," and see results in the Canvas side panel. Users can then ask for additional recommendations, flight times, etc., and even pause and return to search results at a later time. For those looking for an easier way to book restaurant reservations, event tickets, or spa appointments, Google (GOOG) (GOOGL) is launching AI mode with agentic booking. Users can describe what they are looking for and AI mode will search across multiple websites for options and finalize booking through platforms like OpenTable (BKNG), Ticketmaster (LYV), StubHub (STUB), and Booksy. In the future, travelers will also be able to book flights and hotels directly in Google’s (GOOG) (GOOGL) AI mode. Users can compare different options, select preferences, and then book with the partner of their choice, such as Expedia (EXPE), Booking Holdings (BKNG), Choice Hotels (CHH), and Marriott International (MAR). “We’re committed to partnering with travel companies of every size, so you have all the best options at your fingertips,” the company said in a statement. On Mon, Nov 17, 2025 at 10:51 AM Carlos Navarro <[email protected]> wrote: > Hi, > > A great contribution Jacopo, it comes at the right time! > > Thank you so much! > > El lun, 17 nov 2025 a las 15:18, Jacopo Cappellato (< > [email protected]>) escribió: > > > Hi all, > > > > I’d like to share a pet project I have been working on over the past > > few months, and I believe it may be of interest to the OFBiz > > community. > > > > Model Context Protocol (MCP) [*] is an emerging open protocol designed > > to allow AI-driven applications to interact with external tools and > > data sources using natural language prompts. Its goal is to > > standardize how Large Language Models (LLMs) can call external APIs or > > services in a structured and secure way. > > > > I have been exploring how MCP could be applied to Apache OFBiz, and as > > part of this effort I created a GitHub project implementing an MCP > > server for OFBiz: > > > > https://github.com/jacopoc/mcp-server-for-apache-ofbiz > > > > The MCP server communicates with OFBiz through RESTful API calls and > > is intended as a lightweight platform on which new MCP tools can > > easily be implemented. > > Out-of-the-box it currently includes a template tool that calls > > OFBiz’s "findProductById" service, but the architecture is designed to > > make the addition of new tools straightforward. > > > > The idea is that AI applications such as Claude, ChatGPT, Gemini, or > > custom AI agents can "reason" and leverage these tools to interact > > with OFBiz, for example: > > > > “Create a SEO-friendly description of the product WG-1111.” > > > > Some additional project highlights: > > * The MCP server is intentionally decoupled from OFBiz and can be > > deployed either locally or as an external service. > > * It works with ootb OFBiz, no patches required. > > * The project has reached a first milestone: it is now fully compliant > > with the latest MCP specification, and I’ll keep extending it with > > more features and tools. > > > > I am happy to continue maintaining it as an independent project, but I > > am open to discussing a home for it within the OFBiz community if > > there is interest. > > If you’re curious, please take a look, I would really appreciate > > feedback, ideas, or contributions. > > I can also provide the URL of a running instance that you can easily > > attach to an AI application (e.g., Claude) for testing. Just let me > > know if you’d like access or if the README isn’t sufficient to get you > > started. > > > > Thanks for your time, and looking forward to your thoughts! > > > > Best regards, > > Jacopo > > > > [*] https://modelcontextprotocol.io/docs/getting-started/intro > > > -- Bill Harder OsZ Technologies 256 N State St Ste D Hemet, CA 92543 Voice: 818-632-5790 eMail: [email protected] www: www.osz.com
