Current methods for AI agents to interact with websites rely on screen-scraping, which involves reading raw HTML and guessing element functions. This approach is prone to errors when website layouts or CSS classes change, leading to broken automation and unreliable agent performance.
WebMCP proposes a new model where websites explicitly declare their capabilities as structured tools that AI agents can directly call. Instead of interpreting visual elements, agents would use a defined API to interact with functions like 'book_table' with specified parameters, eliminating the need for pixel-reading or guesswork.
WebMCP is a proposed web standard under joint development by Google (Chrome) and Microsoft (Edge) within the W3C Web Machine Learning Community Group. It provides a JavaScript API for web pages to register discoverable and callable tools for AI agents. Currently, it is a Community Group draft, not yet a finished W3C standard.
The standard focuses on three key aspects: Discovery, allowing pages to announce available tools like 'checkout' or 'filter_results'; and Schemas, which define the structure and parameters for each tool. This structured approach ensures agents know how to interact with website features precisely.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
Google and Microsoft are developing WebMCP, a proposed web standard that allows websites to declare their functionalities as structured tools for AI agents. This initiative aims to replace current screen-scraping methods with a more reliable and efficient way for AI to interact with web pages, improving automation and reducing errors.