WebMCP Standard Proposal for Agentic Web Actuation Now Available in Chrome (Origin Trials)
Google has announced that the WebMCP standard proposal is now entering origin trials in Chrome 149, allowing websites to expose tools to in-browser AI agents. This development aims to enhance the reliability of AI interactions by enabling these agents to simulate user actions more effectively, reducing reliance on less reliable methods such as DOM scraping.
WPN Brief
- What Happened
Google has announced that the WebMCP standard proposal is now entering origin trials in Chrome 149, allowing websites to expose tools to in-browser AI agents. This development aims to enhance the reliability of AI interactions by enabling these agents to simulate user actions more effectively, reducing reliance on less reliable methods such as DOM scraping.
- Why It Matters
The introduction of the WebMCP standard is significant for Google as it represents a strategic move to integrate AI more deeply into web interactions, potentially improving user experience and engagement through more accurate and efficient AI functionalities.
- The Bigger Picture
This initiative aligns with broader trends in the tech industry, where companies are increasingly exploring AI-driven solutions to enhance user engagement and streamline processes. The ongoing experimentation with AI modes in Chrome and the introduction of features allowing users to opt out of AI-generated search results reflect a growing emphasis on balancing innovation with user control and privacy.
Related Reports
More coverage on this story
7 reports across the wire
Google experiments with sending Chrome searches straight to AI
Google is currently testing a new feature in Chrome that directs users to AI Mode by default when performing searches, indicating a shift towards integrating artificial intelligence more deeply into its browser functionality.
Google tests making AI Mode the default in Search, then says it was an error
Google recently tested a feature in the Chrome Canary release that would have made AI Mode the default setting for search queries, as reported by Windows Report. However, the company later stated that this was an error, raising concerns among users about the implications of such a change.
Google Launches Colab CLI for Developers, Automation, and AI Agents
Google has launched the Google Colab CLI, a command-line tool designed to enable developers and AI agents to interact with remote Colab runtimes directly from their local terminals. This new feature aims to streamline workflows and enhance automation capabilities in AI development.
Google releases macOS versions of AI Edge Gallery, which lets users run open models on their devices, and AI Edge Eloquent, an on-device voice dictation app (Google Developers Blog)
Google has released macOS versions of its AI Edge Gallery and AI Edge Eloquent applications, enabling users to run the new Gemma 4 12B model locally on their devices. This model is designed to enhance user experience by allowing on-device processing of audio and video without relying on cloud services.
Google's NotebookLM now runs its own cloud computer with code execution and agent-based research
Google has announced a significant upgrade to its AI-powered note-taking application, NotebookLM, which now operates on the Gemini 3.5 Flash model and includes its own cloud computer for code execution and agent-based research. This enhancement allows the tool to autonomously find sources via Google Search, outperforming its predecessor in internal tests by up to 78.2 percent.
Google lets sites opt out of AI search results, knowing most have nowhere else to go
Google has introduced an opt-out feature in its Search Console, allowing website operators to exclude their sites from AI-generated search results, a move that follows pressure from the UK's Competition and Markets Authority (CMA). This feature is significant as AI search features currently reach over 3.5 billion users monthly.
Gemma 4 12B Enables On-Device, Multimodal Agentic Workflows with an Encoder-free Architecture
Google has launched the Gemma 4 12B, an open-source AI model designed to operate on devices with 16GB of RAM, enabling on-device multimodal workflows without the need for an encoder. This model allows users to perform tasks such as data processing, generating visual insights, and building webpages locally.