🍕 This #PiDay, we're shipping a literal pizza pie with our WebMCP "zaMaker!" demo to show how structured tool calls change the game → https://goo.gle/3PaAVEL To get started with the demo, you'll need to: Enable the flag: chrome://flags/#enable-webmcp-testing Install the Model Context Tool Inspector extension. Once you're in, tell us what "pi" you’d build and share your results in the comments below!
Chrome for Developers
Technology, Information and Internet
Helping you build, grow, and innovate on the web.
About us
The official Chrome for Developers LinkedIn account from Google. We want to help you build beautiful, accessible, fast, and secure websites that work cross-browser, and for all of your users.
- Website
-
https://developer.chrome.com/
External link for Chrome for Developers
- Industry
- Technology, Information and Internet
- Company size
- 5,001-10,000 employees
Updates
-
Decide between WebMCP and MCP for your next build → https://goo.gle/40ZV4Qw Find the best fit for your AI architecture: 🧭 WebMCP for frontend interaction 📡 MCP for backend workflows ✨ Optimization for browser agents
-
-
The shift from legacy pages to 'agent-friendly' architecture is officially here 🌐
A common question we heard from developers following the announcement of the WebMCP Early Preview in Chrome was: "When should I use WebMCP vs. the standard Model Context Protocol (MCP)?" We wanted to clarify how these two work together to build the Agentic web, and help you understand when to use each solution: 🌐 WebMCP is designed for the browser environment. It allows a website to natively expose its specific features, like searching a catalog or submitting a form, as structured tools directly to a browser-integrated agent. It uses the user’s active session and the browser’s security model to facilitate these actions. 🛠️ MCP is ideal for connecting agents to data and services that exist beyond the current tab, such as local databases, enterprise APIs, or cloud-based productivity tools. The Takeaway: Use WebMCP to make your specific web application "agent-aware" so users can interact with your site more efficiently. Use MCP to provide the agent with the broader context and data it needs to perform tasks across different platforms. Read the full technical breakdown I wrote with Alexandra K. here: https://lnkd.in/eWjs9wfW #WebMCP #MCP #AIAgents
-
-
🗞️ Extra! Extra 🗞️ Chrome DevTools now has a Model Context Protocol (MCP) server that lets AI agents interact directly with your browser → https://goo.gle/4qwBzKu Learn how to connect tools like Gemini and VS Code to Chrome for real-time debugging. Matthias Rohmer covers how to set up the server and use it to fix performance issues and bugs.
-
-
Automate complex display scenarios with configurable screens → https://goo.gle/4bAgSIZ Headless Chrome now lets you define virtual displays independent of physical hardware for robust testing.
-
-
Debugging network bottlenecks just became significantly more precise with the ability to throttle individual requests in Chrome DevTools → https://goo.gle/4aP1Tcc Instead of applying global throttling that slows down your entire session, you can now target specific API calls or heavy assets to simulate real-world conditions with surgical precision. It’s a major win for testing edge cases without losing your development velocity.
-
The web is moving from human-centric pages to agent-ready tools, and these demos show how → https://goo.gle/3MsLxOB We want to see your work! Submit your custom tools or agents via a PR to be featured in our curated community list.
-
We’re evolving how we ship → https://goo.gle/4bb7YQG To deliver new capabilities and security patches even faster, Chrome is moving to a two-week stable release cycle starting this September. This shift allows for smaller, more manageable updates and simplified debugging, ensuring the web platform moves at the speed of your ideas.
-
-
Meet Gemini 3.1 Flash-Lite: a new standard for intelligent, high-volume AI → https://goo.gle/3OKbxFO Built to handle complex reasoning with minimal latency, this model delivers the precision needed for sophisticated developer workflows without the overhead. Whether you’re focused on data extraction, summarization, or rapid prototyping, Flash-Lite provides an affordable advantage for your next project. It’s also a great engine for working with APIs like CSS Anchor Positioning or View Transitions. Take 10 minutes to explore the new model in Google AI Studio today and share what you built in the comments!