I Bridged My Real Logged-In Browser to Chrome's New WebMCP API

Описание и применение

Пользователь создал webmcp-bridge, который позволяет веб‑страницам использовать реальные браузерные сессии через WebMCP API, обходя ограничения логина и ботов.

Задача

Server‑side fetchers fail on login walls, 403s, and bot detection, making DOM scraping fragile.

Результат

15 smoke tests passed; agents can now read authenticated pages and bypass bot checks by calling real browser tools.

Рабочий процесс

• 1. Install webmcp-bridge via pip.
• 2. Run the local server (127.0.0.1:18765).
• 3. Include the shim script on any page: <script src="http://127.0.0.1:18765/webmcp.js"></script>.
• 4. The shim fetches tool manifests from /webmcp/tools and registers them with document.modelContext.registerTool().
• 5. Agents discover and call the tools like any other page tool.
• 6. For open_and_read_url, the server enforces a domain allowlist defined in ~/.config/webmcp-bridge/config.json.

Доказательства

Chrome's WebMCP proposal (W3C Community Group draft, origin trial from M149) lets a web page declare typed, callable tools via document.modelContext.registerTool() — so an in-browser AI agent can call them directly instead of scraping the DOM.

Источник

I built webmcp-bridge — the first bridge from Browser Buddy to the WebMCP API.

Источник

Two tools ship out of the box: read_active_tab and open_and_read_url.

Источник

Because login walls, 403s, and bot detection defeat server-side fetchers — and DOM scraping is fragile by design.

Источник

The server binds 127.0.0.1 only; the shim is same-origin by design.

Источник

pip install webmcp-bridge webmcp-bridge # http://127.0.0.1:18765/ — demo page included

Источник