Browser Use Adds Support for WebMCP

X postIdan LevinAnnouncement

Agent automation framework Browser Use has added support for WebMCP. Idan Levin documented the update on the WebMCP ecosystem tracker, which monitors the adoption of the proposed standard across browsers, agents, and frameworks.

Key points

  1. Browser Use has rolled out WebMCP support, as announced by Gregor Zunic.
  2. According to Zunic, WebMCP enables fully deterministic interactions for web agents instead of fragile UI-based navigation.
  3. The WebMCP ecosystem tracker has been updated to list Browser Use among compatible frameworks and agents.
  4. On the browser side, Chrome is running an origin trial targeting Chrome 157, Edge offers a trial through 17 November 2026, and Brave supports it behind a flag in Nightly builds.
  5. Firefox maintainer Mozilla remains neutral citing privacy and hidden-instruction concerns, while Apple's WebKit team opposes the proposal.

Why it matters

Web agents that rely purely on visual rendering and DOM scraping often suffer from high failure rates. WebMCP aims to make web interactions deterministic by letting sites expose structured JavaScript functions and forms directly to agents. Fast adoption by developer tooling such as Browser Use drives practical usage ahead of finalised browser standards.

Analysis

The addition of WebMCP in Browser Use highlights increasing developer interest in structured agent-to-web interfaces. However, widespread deployment still hinges on browser adoption: while Chromium variants are progressing through origin trials, opposition from WebKit and reservations from Mozilla show that consensus on privacy, assistive technology parity, and agent detection is still pending.

Original post

idan levin

@0xidanlevin · 6 September 2026

That was fast! Browser Use just added WebMCP support. Already updated on the ecosystem tracker: t.co/FNMqZE1kHp t.co/EdabCW7eNN t.co/HHqOvGTC5H

86 likes2 replies63 bookmarks9.5k views

View on X
More posts in the thread (1)
  1. @umang147 this is exactly what we checked in t.co/MPXjJvRpTE. We have a specific task on checkout
Selected replies (3)
  • @umang147 @0xidanlevin Would love to see the same checkout run with and without WebMCP. Tokens, retries and completion rate. That would tell us how much easier it gets for a cheaper model to actually finish the job.
  • @NeelakandanNC @0xidanlevin That one was unexpected
  • @umang147 @0xidanlevin This is exactly the comparison I was looking for. Good to see cheaper models doing well with a better interface.

Mentioned links

Links and tools from this entry

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Link:webmcp.com

    WebMCP Adoption Tracker: Current Status Across Browsers and AI Agents

    The WebMCP Ecosystem Adoption Tracker monitors the implementation status of the proposed WebMCP standard across browsers and agent runtimes. While OpenAI has enabled WebMCP by default in ChatGPT and Chrome targets release 157, Mozilla remains neutral and WebKit formally opposes it.

    AI & LLMs· Resource

  • Repository:nekuda-ai/WindTunnel

    WindTunnel: Benchmarking Browser Agent Interfaces and WebMCP

    WindTunnel is an open-source benchmark suite designed to compare how browser agents interact with websites. It evaluates WebMCP (direct site-exposed actions) against coordinate-based computer use via screenshots and page structure navigation using DOM and accessibility trees.

    34starsHTML

    AI & LLMs· Research

  • Link:nekuda-ai

    WindTunnel: Open Benchmark Compares WebMCP Against Computer Use and DOM Approaches

    Nekuda-ai has released WindTunnel, a reproducible open-source benchmark evaluating WebMCP against screenshot-based computer use and DOM-based browser agents. Evaluating 49 tasks across eight real websites with three attempts per task, the benchmark tests models including GPT-5.6 Luna, Gemini 3.6 Flash, and Sonnet 5.

    AI & LLMs· Resource

  • Repository:captivus/chrome-agent

    chrome-agent: Direct CDP Control for AI Coding Agents

    chrome-agent is a CLI tool and Python library giving AI coding agents direct browser inspection and interaction via the Chrome DevTools Protocol (CDP). It avoids restrictive abstraction layers and enables concurrent, isolated use by multiple agents and human operators.

    243starsPython

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.