{"slug": "what-is-webmcp-and-why-it-matters", "title": "What is WebMCP (and why it matters)", "summary": "WebMCP, a proposed browser standard incubated at the W3C by Google's Chrome team and Microsoft's Edge team, lets websites expose structured tools that AI agents call directly instead of screen-scraping pages, and it has shipped as an early preview in Chrome 146 behind a flag. The standard builds on the Model Context Protocol used by assistants such as Claude and ChatGPT, but runs inside the browser tab so tools inherit the user's existing cookies and single sign-on; sites can declare tools via HTML attributes like toolname and tooldescription or the navigator.modelContext JavaScript API. WebMCP remains a W3C Community Group draft, is tools-only with no resources or prompts yet, and the spec is expected to change.", "body_md": "[Blog](https://oncroft.net/blog/) · August 27, 2026 · Rich Chetwynd\n\n# What is WebMCP (and why it matters)\n\nWebMCP lets a website hand AI agents structured tools to call directly, instead of screen-scraping and guessing at buttons. What it is, and why it matters.\n\nAI agents are learning to use the web on your behalf — booking a flight, filling a form, pulling a number out of a dashboard. The trouble is *how* they do it today: they take screenshots, parse raw HTML, and guess which button does what. It’s slow, expensive, and it breaks the moment a site changes its layout.\n\n**WebMCP** is the fix. It’s a new browser standard that lets a website hand an AI agent a clean set of **tools** to call directly — no guessing required.\n\n## What WebMCP is\n\nWebMCP (Web Model Context Protocol) is a proposed web standard, incubated at the W3C by Google’s Chrome team and Microsoft’s Edge team. It builds on the same idea as [MCP](https://oncroft.net/connect/) — the Model Context Protocol that assistants like Claude and ChatGPT already use to talk to tools — but brings it into the browser, to the front end of a web page.\n\nInstead of an agent looking at your page and trying to work out what’s clickable, the page simply tells it: *“Here’s a tool called `searchFlights`. It needs an origin, a destination, and a date. Call it, and I’ll give you structured results.”* The agent discovers the tools, reads their definitions, and calls them — replacing a long chain of clicks with a single, reliable function call.\n\n## How it works\n\nA site exposes its tools in one of two ways:\n\n- **Annotate your HTML.** Add attributes like`toolname` and`tooldescription` to an existing form, and the browser turns its fields into a structured schema an agent can understand. Minimal effort for simple things.\n- **Register tools in JavaScript.** Use the new`navigator.modelContext` API to declare tools with a name, a description, an input schema, and a function to run. This handles richer, dynamic cases, and tools can appear or disappear as the page state changes.\n\nTwo details make it neat. It runs **inside the browser tab**, so it inherits the session you’re already in — your cookies and single sign-on — rather than needing a separate login. And because the tools are declared by the site itself, they don’t break when the visual design changes.\n\n## WebMCP vs “regular” MCP\n\nThey’re complementary layers of the same idea:\n\n- **Regular MCP** runs on a**separate server** that an assistant connects to — this is how you build apps on Croft, by pointing Claude or ChatGPT at your croft’s MCP endpoint. It covers tools, resources, and prompts.\n- **WebMCP** runs**in the page** , front-end, and (for now) covers tool-calling only. It’s how a running web app makes*itself* usable by an agent in the browser.\n\nOne is about building and managing software; the other is about letting an agent operate the software once it’s live.\n\n## Why it’s useful\n\n**For the people using agents:** the agent actually gets things done — searching a catalogue, starting a checkout, creating a support ticket, updating a dashboard — quickly and without misclicks.\n\n**For whoever owns the site:** you become usable by the wave of agentic browsers now arriving (Chrome’s auto-browse, OpenAI’s Atlas, and others). Those tools are the *consumers*; WebMCP is the infrastructure a site implements to be *used well* by them. It’s faster and cheaper than being screen-scraped, it doesn’t shatter on a redesign, and it opens your product to a new kind of visitor: an agent working for a real customer.\n\n## Where it’s at (be realistic)\n\nIt’s early. WebMCP is a **W3C Community Group draft, not a finished standard**, and it’s shipped as an early preview in Chrome 146 behind a flag. The spec will change, it’s tools-only for now (no resources or prompts yet), and because it leans on your browser session for auth, sensitive actions need careful thought. This is a “start prototyping and watching” moment, not a “bet production on it today” one.\n\n## What it means for the apps you build\n\nHere’s the part that matters if you build software. The agentic web isn’t only about chat any more — it’s coming to the *front end* of your apps. And that raises a question: when the standard settles, will *your* apps be able to adopt it?\n\nIf your app lives inside a closed platform, you wait for that platform to add it — if it ever does. The apps you build on [Croft](https://oncroft.net/how-it-works/) are different: they’re real web apps that are **yours** — your code, on a server that’s yours. So when WebMCP stabilises, you can add a handful of tool declarations to your internal tools and make them agent-ready on your own timeline, no permission required. And on the build side, Croft is already MCP-native.\n\nThe web is quietly growing a machine-readable layer alongside the human one. WebMCP is how that layer gets built — and owning your apps is how you make sure you can be part of it.\n\n## Stake out your croft.\n\nYour team's first app could be live before lunch.\n\n[Get your croft](https://app.oncroft.net/signup)\n\n7 days free, no card to start. From $24/month - cancel anytime and take everything with you.", "url": "https://wpnews.pro/news/what-is-webmcp-and-why-it-matters", "canonical_source": "https://oncroft.net/blog/what-is-webmcp/", "published_at": "2026-08-26 12:00:00+00:00", "updated_at": "2026-09-24 04:29:13.236669+00:00", "lang": "en", "topics": ["agent-protocols", "ai-agents", "ai-tools", "artificial-intelligence", "developer-tools"], "entities": ["WebMCP", "W3C", "Google Chrome", "Microsoft Edge", "Model Context Protocol", "Claude", "ChatGPT", "Rich Chetwynd"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/what-is-webmcp-and-why-it-matters", "markdown": "https://wpnews.pro/news/what-is-webmcp-and-why-it-matters.md", "text": "https://wpnews.pro/news/what-is-webmcp-and-why-it-matters.txt", "jsonld": "https://wpnews.pro/news/what-is-webmcp-and-why-it-matters.jsonld"}}