Google just announced
that the Gemini SDK is now compatible with MCP tools. What are
those tools?
Google I/O '25 in under 10 minutes - Google Gemini Agent Mode
An experimental version of the Agent
mode in the Gemini app will be coming soon to subscribers.
This is a new and emerging area and we are excited to explore how best to bring the benefits of agents to users. and the ecosystem more broadly.
Google I/O 2025: Sundar Pichai’s opening keynote - https://blog.google/technology/ai/io-2025-keynote/
Check out this short video extract that's focused on one use case, to find shared roommate housing:
Here's some of the key transcript and this powerful use case for the Gemini Agent Mode:
"We are excited to announce that our Gemini SDK is now compatible with MCP tools. These technologies will work together to make agents even more useful and we are starting to bring Agentic capabilities to Chrome search and the Gemini app.
Let me show you what we are excited about in the Gemini app. We call it Agent mode.
Say you want to find an apartment for you and two roommates in Austin. You've each got a budget of $1,200 a month. You want a washer & dryer or at least a Laundromat nearby. Normally, you'd have to spend a lot of time scrolling through endless listings. Using Agent mode, the Gemini app goes to work behind the scenes. It finds listings from sites like Zillow that match your criteria, and uses Project Mariner when needed to adjust very specific filters.
If there's an apartment you want to check out, Gemini uses MCP to access the listings and even schedule a tour on your behalf.
And it'll keep browsing for new listings for as long as you need, freeing you up to do the stuff you want to do, like plan the housewarming party. It's great for companies like Zillow, bringing in new customers and improving conversion rates.
An experimental version of the Agent mode in the Gemini app will be coming soon to subscribers. This is a new and emerging area and we are excited to explore how best to bring the benefits of agents to users and the ecosystem more broadly."
. . .
https://blog.google/technology/ai/io-2025-keynote/
https://www.youtube.com/watch?v=bwwvsvU-670
MCP AI Agents: EASIEST way EVER to Integrate ANY TOOLS!
Mervin Praison
67.6K subscribers
9,051 views since Mar 29, 2025
as of May 27 #MCP #AIagents #GPT4
Build Powerful AI Tools in Minutes with Model Context Protocol (MCP)
Learn how to create your own AI agents using the Model Context Protocol (MCP) standard with just a few lines of code!
This tutorial shows you how to build an Airbnb apartment search tool that demonstrates the power and simplicity of MCP integration.
https://docs.praison.ai/mcp/airbnb
🔑 What is Model Context Protocol (MCP)?
A universal AI tool standard to connect any AI tool with any AI agent
Instantly add dozens of tools to any AI agent
Build custom agents independent from tool providers
Create your own AI infrastructure in minutes, not months
Access thousands of MCP tools to connect to virtually any software
📊 Why MCP Matters
One of the highest trending topics on Twitter
Transforms AI workflows from weeks of integration to minutes of implementation
Join the top 1% of AI developers while others struggle with complex integrations
Early adopters will define the future of AI workflow automation
🛠️ Before vs After MCP
*Before MCP:*
Custom code needed for every tool
Incompatible AI frameworks
Weeks of integration work
*After MCP:*
Simple configuration file
Universal tool standard
Minutes to implement (literally minutes!)
💼 Practical Applications
Imagine waking up tomorrow and your AI agent:
- Automatically searches the web for you
- Manages code repositories without manual commands
- Queries all your databases through natural language
- Organizes all your files while you sleep
🔍 Full Code Available
All code shown in this tutorial is available in the description for you to copy
and paste.
https://docs.praison.ai/mcp/airbnb
https://github.com/modelcontextprotocol/servers
📚 Related Content
Check out my other video on using AI agents as a RAG application - 100% local
and 100% private using Deepseek R1.
Let me know in the comments what you think about this approach to building AI tools!
#AItools #MCP #AIagents #ModelContextProtocol #PythonTutorial #AIprogramming #AIautomation #GPT4 #MachineLearning #OpenAI
Timestamp:
0:00 - Introduction to Model Context Protocol (MCP)
0:32 - What is MCP and its benefits
1:26 - MCP vs traditional approach
2:07 - Step-by-step implementation
2:36 - Code walkthrough for basic setup
3:29 - Creating and integrating MCP agent
3:59 - Running the code and results demo
4:29 - Adding user interface
5:07 - Final thoughts
MCP tools - Agent Development Kit - https://google.github.io/adk-docs/tools/mcp-tools/
. . .
RAG vs.
CAG: Solving Knowledge Gaps in AI Models
IBM Technology 1.2M subscribers
304,425 views since Mar 17, 2025
as of 5/27/25. #aiworkflow #machinelearning #retrievalaugmentedgeneration
Ready to become a certified watsonx Generative AI Engineer? Register now and use
code IBMTechYT20 for 20% off of your exam → https://ibm.biz/BdGtmQ
Learn more about RAG here → https://ibm.biz/BdGtm3
What if your AI can't answer who won the Oscars last year? 🎥 Martin Keen explains how RAG (Retrieval-Augmented Generation) and CAG (Cache-Augmented Generation) address knowledge gaps in AI. 🚀 Discover their strengths in real-time retrieval, scalability, and efficient workflows for smarter AI systems. 💻
AI news moves fast. Sign up for a monthly newsletter for AI updates from IBM → https://ibm.biz/BdGtmw
#retrievalaugmentedgeneration #aiworkflow #machinelearning
. . .
7 tips for getting started with AI agents and automations
AI-powered automation doesn’t have to be overwhelming.
Here are actionable tips to start small and scale thoughtfully.
Melissa Reeve on May 21, 2025 at 9:00 am | Reading time: 6 minutes
Key Takeaways:
1️⃣ Start Small – Begin with simple automation tasks, like summarizing AI news, to build confidence. 2️⃣ Know When to Quit – Not all automation efforts succeed; recognize when manual processes are more effective. 3️⃣ Understand Agents vs. Workflows – Agents make decisions dynamically, while workflows follow a set sequence. 4️⃣ Scale Thoughtfully – Automate repetitive tasks that add up over time to improve efficiency. 5️⃣ Think Like AI – Consider what context AI lacks when troubleshooting automation failures. 6️⃣ Share Knowledge – Communicate automation goals clearly to ensure team adoption. 7️⃣ Refine Automations – Continuously track performance and adjust automation strategies for better results.
The article emphasizes practical AI adoption, encouraging marketers to start small, iterate, and focus on efficiency rather than complexity.
Would you like insights on how to apply these automation strategies to affiliate marketing or lead generation? 🚀
Additional Resources
- MCP AI Agents – MCP tools - Agent Development Kit https://google.github.io/adk-docs/tools/mcp-tools/
- Sundar Pichai’s I/O 2025 keynote – Google I/O 2025: Sundar Pichai’s opening keynote - https://blog.google/technology/ai/io-2025-keynote/
- MCP AI integration tutorial
05/30/2025