WebMCP API extends web apps to AI agents

World Wide Web Consortium (W3C) participants including Google and Microsoft have launched the WebMCP API, a JavaScript interface that allows web applications to provide client-side “tools” to AI agents. The API would enable agents to interact directly with web pages and participate in collaborative workflows with human users within the same web interface.

WebMCP is available for early preview at Google, said Google’s Andre Cipriani Bandarra, developer relations engineer for Chrome and the web in a February 10 blog post. “WebMCP aims to provide a standard way for exposing structured tools, ensuring AI agents can perform actions on your site with increased speed, reliability, and precision,” Bandarra said.

A draft community group report on WebMCP was published on February 12 by the W3C Web Machine Learning Community Group. The WebMCP API is described in the report as a JavaScript interface that lets web developers expose web application functionality as “tools,” meaning JavaScript functions with natural language descriptions and structured schemas that can be invoked by agents, browser’s agents, and assistive technologies. Web pages that use WebMCP can be viewed as Model Context Protocol (MCP) servers that implement tools in client-side script instead of on the back end, enabling collaborative workflows where users and agents work together within the same web interface, according to the report. Editors of the report include Khusal Sagar and Dominic Farolino of Google and Brandon Walderman of Microsoft. The specification is neither a W3C standard nor on the W3C Standards Track, the report says.

Bandarra cited use cases including customer support, ecommerce, and travel, in which agents help users fill out customer support tickets, shop for products, and book flights. Bandarra cited two proposed APIs as part of WebMCP that allow browser agents to act on behalf of the user: a declarative API that performs standard actions that can be defined directly in HTML forms and an imperative API that performs complex and more dynamic interactions that require JavaScript execution. “These APIs serve as a bridge, making your website ‘agent-ready’ and enabling more reliable and performant agent workflows compared to raw DOM actuation,” said Bandarra.