BRYG logo

BRYG

Controls real Chrome or Edge browsers through MCP for navigation, interaction, page reading, OCR, QR decoding, and network capture.

Install BRYG

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "bryg": {
      "command": "npx",
      "args": [
        "-y",
        "bryg-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— the server itself is confirmed live (we called its tools/list endpoint). The stdio install command is a separate, ongoing check.

Overview

BRYG MCP server lets compatible AI clients operate a real Chromium-based browser on the local machine through a plain stdio MCP process. It supports tabs, navigation, accessibility snapshots, text and link extraction, mouse and keyboard actions, uploads, JavaScript evaluation, screenshots, OCR, QR decoding, and network observation. Reach for it when an agent needs to interact with websites as a visible browser user, including authenticated workflows and pages that require visual or coordinate-based actions. Chrome is supported on macOS, Windows, and Linux; Edge is available through the browser selection on supported setups, while Linux uses Chrome.

Use cases

  • Automate authenticated website workflows
  • Inspect and interact with dynamic web pages
  • Extract text, links, screenshots, or OCR results
  • Test forms, dialogs, uploads, and browser navigation
  • Capture and filter browser network traffic

Key features

  • Real Chromium browser control
  • Accessibility snapshots with stable element references
  • Credential filling without exposing secrets to the conversation
  • OCR and QR-code decoding
  • Screenshot and JavaScript evaluation support
  • Network capture with sensitive-field masking

Tools43

What BRYG lets your agent do. Expand a tool for its parameters.

Verified live~4.6k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

8/8 checks healthy over the last 62d

What it can do

From the 43 tools this server returned when we ran it.

Writes files · 1Handles credentials · 5Makes network requests · 5Read-only tools · 42
Network at startup4 connections
Files written at startup3
Install scriptsNone
npm provenanceNot published
Package age67 days
Maintainers1

Observed 2026-10-18 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 16d ago via OSV.dev · bryg-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads350Package downloads in the last 30 days.
Last commit4d agoMost recent push to the default branch.
Tools exposed43Callable tools this server registers over MCP.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How BRYG works

What BRYG does

BRYG exposes browser automation through MCP, allowing an AI client to control a dedicated Chromium browser running on the local machine. Its tools cover browser and window management, page navigation, accessibility inspection, reading, screenshots, mouse actions, keyboard input, form controls, file uploads, and page-side JavaScript evaluation.

The server is suited to interactive web workflows rather than API-only access. An agent can inspect a page, identify interactive elements from an accessibility-tree snapshot, act on stable references, and verify the resulting page state. Coordinate-based actions are also available when element references are not suitable.

BRYG includes OCR for text rendered in images, canvas elements, or games, plus QR-code decoding. Network observation can record browser traffic, apply keyword filters, or focus on failures. Captured sensitive headers and password- or token-like fields are masked by default.

How it works

BRYG runs as a plain stdio MCP server. The client starts the bryg executable, then sends tool calls over MCP. Browser actions are routed to the selected page, and a page opened in a new browser or window can be addressed by its page identifier.

The browser is designed to run headful so a person can watch and take over the session. On Linux without a display, it switches to headless operation. Separate isolated windows can maintain different cookies and login states, which allows multiple accounts to be used at once until the browser closes.

Credentials can be supplied through a credentials file or directly to the login-fill tool. BRYG fills detected username and password fields but does not submit the form; a separate click action is used for submission. This keeps secrets out of the assistant conversation.

Setup and configuration

Install with the macOS/Linux shell installer or the Windows PowerShell installer. The installer places the platform-specific binary under ~/.bryg/bin/ or %USERPROFILE%\\.bryg\\bin\\, verifies its SHA-256 checksum, and guides client registration, optional OCR installation, and license activation.

A direct MCP configuration can use the bryg-mcp npm launcher, which requires Node.js 18 or newer:

config.json
{
  "mcpServers": {
    "bryg": { "command": "npx", "args": ["-y", "bryg-mcp"] }
  }
}

The launcher downloads the matching engine on first use and stores it under ~/.bryg/bin/. Activation uses npx bryg-mcp activate <key>, or the installed CLI can run bryg activate <key>. A license key is required; the product offers a 14-day trial and paid per-device licensing.

The guided setup registers BRYG with Claude Code and Claude Desktop. Other MCP clients can start the binary directly as a stdio server. On Linux, Google Chrome is used; Chrome for Testing can be unpacked into ~/.bryg/chrome-linux64/ when a system installation is unavailable.

Tools and capabilities

  • List, open, activate, and close browser tabs across Chrome and Edge.
  • Create normal, new-window, or isolated browser sessions.
  • Navigate, reload, and traverse browser history.
  • Inspect URL, title, viewport, scroll position, accessibility structure, text, and links.
  • Click by visible text, element reference, or coordinates; also double-click, right-click, hover, drag, and long-press.
  • Type, replace, fill, focus, select options, upload files, scroll, and press key combinations.
  • Capture screenshots, including full-page images, and optionally save them to disk.
  • Run JavaScript in the page and return JSON results.
  • Perform credential filling, OCR, QR decoding, and network capture.

Limitations and notes

BRYG is commercial software distributed under an End User License Agreement; its binary is not open source. The server runs locally, but it makes network calls for license validation and an anonymous update check. A dedicated browser session can be watched and controlled manually, while isolated login state lasts only until the browser closes. Linux operation requires Chrome or a compatible unpacked Chrome for Testing installation, and automatically uses headless mode when no display is available.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about BRYG

BRYG is an MCP server that connects AI assistants to real Chromium-based browsers on the local machine. Its main tools manage tabs, navigate pages, inspect accessibility trees, click and fill forms, type, take screenshots, read content, run JavaScript, perform OCR, decode QR codes, and capture network traffic.

Install BRYG with the macOS/Linux shell installer or Windows PowerShell installer. The guided setup downloads and verifies the platform binary, can register supported MCP clients, optionally installs OCR support, and asks for activation. You can also configure the `bryg-mcp` npm launcher with Node.js 18 or newer.

Yes, BRYG works with Cursor because it is a standard stdio MCP server. Configure Cursor to start the installed `bryg` executable, or use the documented `npx -y bryg-mcp` launcher configuration. The server can also be registered automatically with Claude Code and Claude Desktop.

Yes, BRYG can fill detected username and password fields without placing the credentials in the assistant conversation. It only fills the fields, so the agent must separately click the login control to submit. Isolated browser windows provide separate cookies and login state for multiple accounts.

Yes, BRYG automatically runs headless on Linux when no display is available. It drives Google Chrome on Linux; if Chrome is not installed and root access is unavailable, Chrome for Testing can be unpacked into `~/.bryg/chrome-linux64/`.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewBRYG AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/bryg?style=directory)](https://allmcps.com/mcp/bryg)
HTML Embed
<a href="https://allmcps.com/mcp/bryg"><img src="https://allmcps.com/api/badge/bryg?style=directory" alt="BRYG on AllMCPs" /></a>