WebMCP Ecosystem Adoption Tracker.

Blink

Chrome Status lists WebMCP shipping in Chrome 157, which reaches everyone on 3 November 2026. Until then you can use it in production by signing up for the origin trial, which covers Chrome up to 156.

Two dates worth knowing if you are shipping tools now: the trial's last version, 156, goes out on 20 October, and 157 follows on 3 November. Chrome Status still marks the feature "Proposed" with standards review pending, so 157 is the plan of record rather than a signed guarantee.

For local testing: chrome://flags/#enable-webmcp-testing. Chrome Status

Blink

Microsoft runs its own origin trial, open through 17 November 2026. Register your domain and switch it on with a meta tag or an HTTP header.

Microsoft has not published which Edge version it starts in, so we are not quoting one. Being the same engine as Chrome, platform support tracks Chrome's. Trial

Blink

Desktop and Android, behind a flag, and left out of the release notes. Brave is the only browser where both halves exist at all: the API is there, and its own assistant reads it. Both sides are experimental, so see the Leo row before relying on it. Issue #55232

Open source · headless engine built for agents

The odd one out here: not a browser people use, but an engine you point an agent at. WebMCP is built into it rather than bolted on. Pages can register tools, and an agent connected to it can list and run them. Shipped in release 0.3.6 in July.

The catch is why this is not marked as working: it only offers the API at the old address, on navigator rather than document. A page written against the current spec, including anything using the common compatibility shim, registers nothing at all here. Source

Gecko

Mozilla sees the benefits but is not implementing it. Their filed concerns include the risk of a site passing an agent instructions a person would not see, and of collecting data through what people enter into tools. They have asked for the extension and automation side to be worked through first. Position

WebKit

WebKit has filed an opposing position. Their reasoning is that an agent acting for someone is closer to assistive technology such as a screen reader, and that sites should not be able to detect one and treat it differently. They have suggested the proposal be reconsidered in a new working group, beginning with a workshop at TPAC in October. Position

Agentic browsers

We found nothing either way. All are built on Chromium, so the API may be present behind the usual flag. That is not the same as the product supporting it, so we have left the row open.

Brave · assistant built into the browser

The closest thing to an everyday agent calling page tools, though it should not be read as shipped. The work was filed as an experiment, it sits behind a feature flag, and it was deliberately kept out of the release notes. When QA asked for a test plan, the Brave engineer who built it replied: "I might mark it as QA/Blocked … as it still feels very experimental." It is aimed at a 1.94 beta.

How far off it is: the code checks Chromium's own WebMCP switch before doing anything, and that switch is off unless someone turns it on. We could not find a brave://flags entry for it, or anywhere Brave turns it on for users, so as best we can tell you would have to launch the browser with a command-line switch. The injected script is written to quietly do nothing if the feature is off.

Brave separately pushes its own tool definitions into sites that never added WebMCP, so Leo can end up holding tools you did not write. That code is real and readable, and it is behind the same switch. Issue #55232

Google · assistant built into the browser

Google introduced WebMCP at I/O in May as "a proposed open web standard that allows you to expose structured tools like JavaScript functions and HTML forms to browser-based agents". That was about the standard, not about Gemini using it. We could not find any Google source, then or since, saying Gemini in Chrome consumes WebMCP tools.

Two supporting details: Chrome's docs note that even their own WebMCP test agent, the inspector extension, is separate from Gemini in Chrome. And Chrome's agent reaches pages a different way, pointing at page elements and screen positions. I/O post

Anthropic · extension used by Claude Code, Cowork and Claude Desktop

Anthropic's docs describe how it reads a page: page text, the document, console and network messages, and screenshots. Tools your page registers are not among them.

Confirmed in practice by someone running a site in the origin trial, whose trial registration we verified: "the extension surfaces nothing from navigator.modelContext. … Invocation works; discovery doesn't exist." It falls back to screenshots even when a page publishes tools. That request is open; an earlier one was closed by an inactivity bot rather than by a decision, and nobody from Anthropic has commented on either. Issue #76809

One row covers a lot here. Claude Code, Cowork and Claude Desktop all browse through this same extension, so none of them sees your tools either.

OpenAI · cloud browser

OpenAI's new agent tier for longer multi-step work. When no connector fits a task, it visits public websites from a browser hosted on OpenAI's side. Nothing public says whether it can call tools a page registers.

Worth knowing what it will not do, in their words: "At launch, cloud browser works only on public pages. It does not accept credentials, use autofill or password managers, sign in to websites, or complete payments." So anything behind a login is out of scope for now. Docs

This replaces two things you may be looking for: the old agent mode, now retired, and the Atlas browser, which OpenAI says stops working on 9 August 2026. Atlas notice

OpenAI · built-in browser, macOS and Windows

A real browser inside the ChatGPT app, with its own sign-ins, autofill, extensions and downloads. Both Work and Codex chats use it, and you can watch and annotate the page as it goes. No public information on whether it reads page-registered tools. Docs

OpenAI · Codex Chrome extension

For tasks needing your existing Chrome profile, signed-in sessions and open tabs. Codex's own source shows its desktop browsing is driven through the Chrome DevTools protocol, which is the same channel every working WebMCP implementation uses — so the plumbing is there. We found no evidence it uses it for page tools. Docs

Perplexity · agentic browser

It reads pages through the accessibility tree and screenshots. We found no mention of WebMCP anywhere. If we have this wrong, send us a link and we will fix it.

Opera · agentic browser

Neon exposes the browser to outside tools. That is the opposite direction from what this page measures, which is a browser using the tools a page offers.

Browser extensions

By far the biggest audiences on this page, and no sign of WebMCP in any of them. Extensions cannot really do this yet: there is still no standard way for one to read a page's tools. See the note under Frameworks.

Browserbase · open source

We installed the released package and ran it against current stable Chrome: it found a page's tool and called it, with no setup on our part. The methods are page.listWebMCPTools() and page.invokeWebMCPTool(), shipped in June.

Two limits worth knowing. This is TypeScript only — the published Python and Go packages have no WebMCP support, and the shorter page.tools() name people quote is on an unreleased branch. And the autonomous agent cannot see these tools at all, so prompting will not get it to use them; you call the tool API from your own code. Untested on Browserbase's rented browsers. PR #2178

Google · MCP server

One tool lists what a page offers, another runs it. You have to switch it on with --categoryExperimentalWebmcp and start Chrome with the matching feature flags, so it is off until someone does that. Once on, this is how coding agents such as Claude Code and Cursor reach your tools. Source

Google · library

Reads and runs page tools directly, and is marked experimental. It does not set the browser flag for you — you pass --enable-features=WebMCP yourself. DevTools MCP is built on this layer, so anything on Puppeteer can pick up support by upgrading. Guide

Cloudflare · cloud browser

It works, but only in their experimental --lab pool, not in production, and it reads the older version of the API. Two things to keep straight: their agents SDK does the opposite job, pushing tools into pages. So Cloudflare shows up on both sides. Docs

Microsoft · framework

Nothing in the code or the documentation. Someone did request it in April 2026, and a Playwright maintainer closed the request the next day as not planned, with the reasoning: "This sounds interesting. Let's see if it gains any adoption first." Nothing has changed since. Playwright sees roughly 78 million downloads a week and many agent frameworks are built on it, so this is a notable gap rather than a small one. Issue #40234

Open source · agent framework

A thorough implementation was opened on 11 February, exposing page tools as actions the agent could take directly. The pull request was closed unmerged on 12 April by the repository's inactivity bot, with no maintainer objection recorded. The current code contains no WebMCP support. PR #4085

Firecrawl · cloud agent

No WebMCP anywhere in the product or the docs. What exists is a blog post from July showing a manual recipe: because their browser endpoint runs a real browser in the cloud, an agent can script calls to a page's tools through it. Their own words for why it works: "with no special integration on Firecrawl's end."

Useful if you are running a headless agent and want to reach WebMCP tools anyway. Just not a feature they ship. Blog post

Browserbase · cloud browser you rent

Nothing in the platform, in Director, or in their MCP server, even though Browserbase is who makes Stagehand.

It goes further than "undocumented". Stagehand only switches WebMCP on when it starts a browser on your own machine. Browserbase's rented sessions give you settings for things like screen size, proxies and stealth, but no way to pass browser start-up flags at all — and their docs never say which Chrome version they run, only that they patch it automatically. So there is no route to WebMCP on their cloud today. Session API