By now, you’re certainly all familiar with the Model Context Protocol (MCP)? It’s the standard for connecting Large Language Models (LLMs) to tools and data. But if you look at the current ecosystem, you’ll see a lot of Python and TypeScript…

As a Java developer, you might be wondering: How can I easily and quickly run my own MCP servers?

On this blog, I’ve explained how to develop MCP servers with Quarkus and Micronaut. But thanks to a recent community contribution to LangChain4j, and the simplicity of JBang, building a local MCP server in Java is even easier and with zero boilerplate.

Today, let’s come back to one of my favorite generative AI topics: Retrieval Augmented Generation, or RAG for short.

In RAG, the quality of your generation (when an LLM crafts its answer based on search results) is only as good as your retrieval (the actually retrieved search results).

While vector search (semantic) and keyword search (BM25) each have their strengths, combining them often yields the best results. That’s what we often call Hybrid Search: combining two search techniques or the results of different searches with slight variations.

If you’ve recently vibe-coded and exported a Gemini-powered app from Google AI Studio to host it online on Google Cloud Run, you might have noticed a server/ directory containing a Node.js application. This isn’t just a simple file server; it’s a clever “transparent proxy” designed to solve a classic problem in frontend AI development:

How do I use my API key without leaking it to the browser?

In this post (although vibe-coding is supposed to be all about not looking at the code at all) we’ll dissect exactly how this architecture works, why it’s safer than a client-side key, and where its security limits lie.

A few days ago, LangChain4j 1.11.0 was released, and with this version, a few notable enhancements to the support of the Gemini model family have landed. Let’s dive in!

New Image Generation Models (Gemini 2.5 & 3.0 Preview, aka 🍌 Nano Banana)

Note: Before showing some snippets of code, let me give you the link to the full documentation on the new image model: docs.langchain4j.dev/integrations/image-models/gemini

There’s a new GoogleAiGeminiImageModel class which allows text-to-image generation and image editing using the latest 🍌 Nano Banana models.

Back in 2019, I spent significant time researching Webhooks. In particular, I was interested in best practices, pitfalls, design patterns, and approaches for implementing Webhooks in a reliable, resilient, and effective way.

Everything is distilled in that article: Implementing Webhooks, not as trivial as it may seem

It likely took me a full week to dive deep into this subject, finding sources and experimenting with design patterns myself. But nowadays, AI makes it easier to dive deeper into topics, explore unfamiliar aspects, and share findings with your team.

The Agent Client Protocol (ACP) allows you to connect external AI agents directly into IDEs and text editors that support that protocol (like JetBrains’ IntelliJ IDEA, PyCharm, or WebStorm, as well as Zed). This means you can bring the power of the Gemini CLI directly into your editor, allowing it to interact with your code, run terminal commands, and use Model Context Protocol (MCP) servers right from the AI Assistant chat window.

A month ago, I wrote about building a research assistant in Java, using the Gemini Interactions API, and the Deep Research agent. Today I wanted to revisit this project, but with the goal to make it more user-friendly, with a Javelit based frontend.

The Research Pipeline: From Query to Infographic

• First, the user enters the subject of the research.
• A button action triggers the research of possible topics about that subject (ie. the different possible facets or angles of the subject), using Gemini 3 Flash with Google Search activated.
• The user selects the facets they’re interested in, to restrict the research to only those aspects.
• Then the Deep Research agent kicks in, via the Gemini Interactions API, and spends a few minutes researching the topic.
• Once the final report is ready, Gemini 3 Pro creates a solid summary.
• The summary is used to generate a sketchnote with Nano Banana Pro.

A Look at the User Interface

Let’s say, as a user, I want to research information about the OpenClaw / MoltBot / ClawdBot personal AI assistant (unless it has again changed its name? 😃)

Have you ever wanted to turn your cool LLM prompts & tools, research notes, automation ideas, or even a simple “todo” list into an executable script? Inspired by a HackerNews post about executable Markdown, I’m happy to share gcli-mdrun, a smart little script that allows you to transform standard Markdown files into executable scripts powered by Gemini CLI.

This project allows you to create AI-driven automation, pipelines, and autonomous bots using mere Markdown text files. You can find the project on GitHub at https://github.com/glaforge/gcli-mdrun.

For my recent presentation at SnowCamp on AI Standards & Protocols for AI Agents, I decided to build an MCP server to access the arXiv research paper website where pre-print versions are published and shared with the community.

My goal was to shed light on some lesser-known aspects of the Model Context Protocol:

• 🛠️ While the majority of MCP servers use the tools feature to expose actions that LLMs can request to call,
• 📄 An MCP server can also share resources (and resource templates), exposing various static assets the AI app might be interested in,
• ✏️ And prompts (and prompt templates) that users can access and reuse to utilize the MCP server effectively.

Note: For the impatient, feel free to go straight to the GitHub repository for the full source code. The README.md file gives instructions on how to build, run, configure, and use the server.

Read more...

First of all, dear readers, let me wish you a happy new year! This is my first post on this blog for 2026. I’m looking forward to continuing sharing interesting content with you.

During my holiday break, I wanted to put my recent Java implementation of the Gemini Interactions API to the test. I implemented and released it with the help of Antigravity. My colleague Shubham Saboo and Gargi Gupta wrote a tutorial on how to build an AI research agent with Google Interactions API & Gemini 3. I thought this was a great opportunity to replicate this example in Java using my Interactions API Java SDK.