✅ MCPBrowser (MCP Browser)

MCPBrowser is an MCP browser server that gives AI assistants the ability to browse web pages using a real Chrome or Edge browser. This browser-based MCP server lets AI assistants (Claude, Copilot) access any website — especially those protected by authentication, CAPTCHAs, anti-bot restrictions, or requiring JavaScript rendering. Uses your real Chrome/Edge browser session for web automation, so you log in once, and your AI can navigate, click buttons, fill forms, and extract content from sites that block automated requests.

Built on the Model Context Protocol (MCP), this web browser MCP server works seamlessly with Claude Desktop, Claude Code (CLI), GitHub Copilot, and any MCP-compatible AI assistant. It handles corporate SSO, CAPTCHAs, Cloudflare protection, SPAs, dashboards, and any site that blocks automated requests. Your AI gets the same browser access you have — no special APIs, no headless browser detection, just your authenticated browser session.

Example workflow for AI assistant to use MCPBrowser

Contents

• Requirements

• Installation

  • Amp

  • Claude Code

  • Claude Desktop

  • Cline

  • Codex

  • Copilot CLI

  • Cursor

  • Factory

  • Gemini CLI

  • Goose

  • Kiro

  • LM Studio

  • opencode

  • Qodo Gen

  • VS Code (GitHub Copilot)

  • VS Code Extension

  • Warp

  • Windsurf

• MCP Tools

  • fetch_webpage

  • click_element

  • type_text

  • get_current_html

  • close_tab

• Configuration

• Troubleshooting

• For Developers

• Links

• License

Requirements

• Chrome or Edge browser

• Node.js 18+ (includes npm)

Note: Node.js must be installed on your system. The VS Code extension and npm package both require Node.js to run the MCP server. Download from nodejs.org if not already installed.

Installation

Getting started

First, install MCPBrowser with your MCP client.

Standard config works in most tools:

Amp

Add via the Amp VS Code extension settings screen or by updating your settings.json file:

Amp CLI Setup:

Claude Code

Use the Claude Code CLI to add the MCPBrowser MCP server:

Verify it's working:

You should see:

Claude Desktop

Add to your config file:

Windows: %APPDATA%\Claude\claude_desktop_config.json
Mac: ~/Library/Application Support/Claude/claude_desktop_config.json

Restart Claude Desktop after saving.

Cline

Follow the instruction in the section Configuring MCP Servers.

Add the following to your cline_mcp_settings.json file:

Codex

Use the Codex CLI to add the MCPBrowser MCP server:

Alternatively, create or edit the configuration file ~/.codex/config.toml and add:

For more information, see the Codex MCP documentation.

Copilot CLI

Use the Copilot CLI to interactively add the MCPBrowser MCP server:

Alternatively, create or edit the configuration file ~/.copilot/mcp-config.json and add:

For more information, see the Copilot CLI documentation.

Cursor

Or install manually:

Go to Cursor Settings -> MCP -> Add new MCP Server. Name to your liking, use command type with the command npx -y mcpbrowser@latest. You can also verify config or add command like arguments via clicking Edit.

Factory

Use the Factory CLI to add the MCPBrowser MCP server:

Alternatively, type /mcp within Factory droid to open an interactive UI for managing MCP servers.

For more information, see the Factory MCP documentation.

Gemini CLI

Follow the MCP install guide, use the standard config above.

Goose

Or install manually:

Go to Advanced settings -> Extensions -> Add custom extension. Name to your liking, use type STDIO, and set the command to npx -y mcpbrowser@latest. Click "Add Extension".

Kiro

Follow the MCP Servers documentation. For example in .kiro/settings/mcp.json:

LM Studio

Or install manually:

Go to Program in the right sidebar -> Install -> Edit mcp.json. Use the standard config above.

opencode

Follow the MCP Servers documentation. For example in ~/.config/opencode/opencode.json:

Qodo Gen

Open Qodo Gen chat panel in VSCode or IntelliJ → Connect more tools → + Add new MCP → Paste the standard config above.

Click Save.

VS Code (GitHub Copilot)

Or install manually:

Follow the MCP install guide, use the standard config above. You can also install the MCPBrowser MCP server using the VS Code CLI:

After installation, the MCPBrowser MCP server will be available for use with your GitHub Copilot agent in VS Code.

VS Code Extension

Install from VS Code Marketplace or run:

The extension automatically installs and configures everything for GitHub Copilot.

Warp

Go to Settings -> AI -> Manage MCP Servers -> + Add to add an MCP Server. Use the standard config above.

Alternatively, use the slash command /add-mcp in the Warp prompt and paste the standard config from above.

Windsurf

Follow Windsurf MCP documentation. Use the standard config above.

MCP Tools

fetch_webpage

Fetches web pages using your Chrome/Edge browser. Handles authentication, CAPTCHA, SSO, anti-bot protection, and JavaScript-heavy sites. Opens the URL in a browser tab (reuses existing tab for same domain) and waits for the page to fully load before returning content. Automatically detects SPAs (React, Vue, Angular) and waits for JavaScript to render content.

Parameters:

• url (string, required) - The URL to fetch

• removeUnnecessaryHTML (boolean, optional, default: true) - Remove unnecessary HTML for size reduction by ~90%

• postLoadWait (number, optional, default: 0) - Additional milliseconds to wait after page load before extracting HTML. Use for pages that need extra time to render.

Examples:

click_element

Clicks on any clickable element (buttons, links, divs with onclick handlers, etc.). Can target by CSS selector or visible text content. Automatically scrolls element into view and waits for page stability after clicking.

⚠️ Note: Page must be already loaded via fetch_webpage first.

Parameters:

• url (string, required) - The URL of the page (must match a previously fetched page)

• selector (string, optional) - CSS selector for the element (e.g., #submit-btn, .login-button)

• text (string, optional) - Text content to search for if selector not provided (e.g., "Sign In", "Submit")

• returnHtml (boolean, optional, default: true) - Whether to wait for stability and return HTML after clicking. Set to false for fast form interactions (checkboxes, radio buttons)

• removeUnnecessaryHTML (boolean, optional, default: true) - Remove unnecessary HTML for size reduction. Only used when returnHtml is true

• postClickWait (number, optional, default: 1000) - Milliseconds to wait after click for SPAs to render dynamic content

• waitForElementTimeout (number, optional, default: 1000) - Maximum time to wait for element in milliseconds

Examples:

type_text

Types text into an input field, textarea, or other editable element. Simulates human-like typing with configurable delay between keystrokes. Automatically clears existing text by default.

⚠️ Note: Page must be already loaded via fetch_webpage first.

Parameters:

• url (string, required) - The URL of the page (must match a previously fetched page)

• selector (string, required) - CSS selector for the input element (e.g., #username, input[name="email"])

• text (string, required) - Text to type into the field

• clear (boolean, optional, default: true) - Whether to clear existing text first

• typeDelay (number, optional, default: 50) - Delay between keystrokes in milliseconds (simulates human typing)

• returnHtml (boolean, optional, default: true) - Whether to wait for stability and return HTML after typing

• removeUnnecessaryHTML (boolean, optional, default: true) - Remove unnecessary HTML for size reduction. Only used when returnHtml is true

• postTypeWait (number, optional, default: 1000) - Milliseconds to wait after typing for SPAs to render dynamic content

• waitForElementTimeout (number, optional, default: 5000) - Maximum time to wait for element in milliseconds

Examples:

get_current_html

Gets the current HTML from an already-loaded page WITHOUT navigating or reloading. Much faster than fetch_webpage since it only extracts the current DOM state. Use this after interactions (click, type) to get the updated page content efficiently.

⚠️ Note: Page must be already loaded via fetch_webpage first.

Parameters:

• url (string, required) - The URL of the page (must match a previously fetched page)

• removeUnnecessaryHTML (boolean, optional, default: true) - Remove unnecessary HTML for size reduction by ~90%

Examples:

Performance comparison:

• fetch_webpage: 2-5 seconds (full page reload)

• get_current_html: 0.1-0.3 seconds (just extracts HTML) ✅

close_tab

Closes the browser tab for the given URL's hostname. Removes the page from the tab pool and forces a fresh session on the next visit to that hostname. Useful for clearing authentication state, managing memory, or starting fresh with a domain.

⚠️ Note: Uses exact hostname match (www.example.com and example.com are treated as different tabs).

Parameters:

• url (string, required) - The URL whose hostname tab should be closed

Examples:

Use cases:

• Clear authentication/session state

• Free up browser memory

• Reset to fresh state before new login

Configuration (Optional)

Environment variables for advanced setup:

Troubleshooting

Browser doesn't open?

• Make sure Chrome or Edge is installed

• Try setting CHROME_PATH explicitly

Can't connect to browser?

• Close all Chrome instances and try again

• Check if port 9222 is in use

Authentication not preserved?

• Keep the browser tab open (default behavior)

• Use the same domain for related requests

For Developers

For Developers

Clone and setup:

Run tests:

Links

• GitHub

• npm

• VS Code Marketplace

• Issues

License

MIT