# WebMCP: Letting Agents Act Inside Your Web Page | WebPossible

> WebMCP brings the Model Context Protocol into the browser, letting a site expose callable tools to an agent on the page. What it is, how it works, and why it is early but important.

Source: https://webpossible.com/webmcp/
Format: Markdown version for AI agents. The canonical HTML page is at the source URL above.

---

[Home](/) / WebMCP

# WebMCP

Server-side MCP lets agents call your backend. WebMCP extends the same idea into the page itself, so an agent can submit a form or start a checkout without screenshotting your screen and guessing. It is early, and it is where this is going.

[Read the MCP guide](/model-context-protocol/)

Today, an agent operating in a browser mostly has to look at a rendered page and infer how to use it, clicking buttons and filling fields the way a person would, with all the fragility that implies. WebMCP replaces the guessing. A site exposes named, described tools, and the agent calls them directly, the same pattern as the [Model Context Protocol](/model-context-protocol/), brought into the page.

It can be declarative, through attributes on your HTML, or imperative, through a JavaScript interface for richer apps. Either way, the agent stops puppeteering your UI and starts using a real interface.

## Why it matters even though it is early

WebMCP is still maturing in browsers and is not yet a production default. So why care now? Because the brands that learn it early will be the ones agents can operate first, and that head start matters most in [agentic commerce](/agentic-commerce/), where the agent that can complete a checkout cleanly wins the sale. Get the readable and citable layers right first, then move into being callable. The whole progression is laid out in [agent legibility](/agent-legibility/).

## WebMCP, answered

What is WebMCP?

WebMCP brings the idea of the Model Context Protocol into the browser. It lets a website expose callable tools to an AI agent operating inside the page, through HTML attributes or a JavaScript interface, so the agent can act directly instead of clicking around a rendered page or guessing at the DOM.

How is WebMCP different from a server MCP?

A server MCP exposes tools from your backend, callable by agents anywhere. WebMCP exposes tools within a live web page, for an agent operating in the browser context with the user. They are complementary: the server handles backend actions, WebMCP handles in-page interaction.

Is WebMCP ready to use today?

It is early and still maturing in browsers, often behind flags, so it is not yet a production default. But it is the clearest signal of where agent interaction with the web is heading. Understanding it now positions you to be among the first sites agents can operate cleanly.

[See the agent legibility framework](/agent-legibility/)