What you can do with Remote Browser

Built for

Browser Automation, Web QA, Public-Site Testing, Agent Workflows

Example workflows

Review a public landing page

Uses a zero-install cloud browser for page review.

Try this

Open this public URL in the remote browser, capture a screenshot, summarize the first fold, and list visible conversion issues.

Test an interactive flow

Turns cloud browser automation into product QA.

Try this

Navigate through this product flow, click the primary calls to action, and report where the browser gets blocked.

Analyze a remote MCP server

Combines browsing and visual inspection for research.

Try this

Load the page, read visible text, take a screenshot, and summarize the main claims, navigation options, and missing context.

Reach a local tunnel

Covers the cloud-browser path for local apps exposed through a tunnel.

Try this

Open my exposed localhost tunnel in the remote browser and capture the first-fold screenshot after the page finishes loading.

Context to know first

What is Remote Browser best for?

It is best for zero-install browser automation against public websites or tunnel-exposed local apps, using a cloud-hosted Chrome session.

How is Remote Browser different from Local Browser?

Remote Browser runs Chrome in the cloud and needs a tunnel for localhost. Local Browser runs on the user's machine and reaches localhost directly.

Can it capture screenshots?

Yes. The remote browser can take screenshots and return visual content for agents to inspect during page review and QA workflows.

AI Skill
SKILL.md

Domain knowledge for Remote Browser — workflow patterns, data models, and gotchas for your AI agent.

Remote Browser (Steel)

Drive a hosted Chromium instance: multi-tab navigation, pointer and keyboard automation, form completion, uploads, and iframe-aware actions. Capture accessibility snapshots or raster screenshots for grounding, stream console logs and network activity, and run arbitrary page scripts when needed.

Data Model

  • Navigation — URLs, history, and tab lifecycle.
  • Input — clicks, drags, typing, key chords, selects, and multi-field forms.
  • Observability — DOM/accessibility trees, PNG captures, HAR-style network summaries, console streams.
  • Automation hooks — scripted evaluation, waits, viewport tweaks, dialog handling.

Gotchas

  • Local services: Reach developer machines through the desktop proxy tunnel (mcpbundles proxy expose <port>).
  • Ephemeral VMs: Sessions expire—re-open pages after long idle gaps.

Tools in this Server (35)

Browser Click

Perform click on a web page

Browser Click And Switch Tab

Click a link that opens in a new tab and switch to it. Use for links with target=_blank or Ctrl+click to force new tab.

Browser Close

Close the current page or the entire browser session. Use to release resources when done with browser automation.

Browser Console Messages

Returns console messages. Note: Only messages logged AFTER browser session started are available.

Browser Drag

Perform drag and drop between two elements

Browser Emulate

Emulate network conditions and CPU throttling to test performance on slow connections or devices

Browser Evaluate

Evaluate JavaScript expression on page or element

Browser File Upload

Upload files to a file input or upload button using base64-encoded file payloads.

Browser Fill Form

Fill multiple form fields

Browser Get Console Message

Get detailed information about a captured console message including structured arguments, stack trace, and source location.

Browser Get Cookies

Get browser cookies including HttpOnly cookies. Returns name, value, domain, path, expires, httpOnly, secure, and sameSite for each cookie. Useful for...

Browser Get Network Request

Get detailed information about a captured network request: status, response headers, timing, and a truncated text body when available.

Browser Get Storage

Read localStorage or sessionStorage from the current page. Returns all key-value pairs or a specific key. Useful for extracting auth tokens, user pref...

Browser Get Visible Text

Get the visible text content of the current page. Lighter than browser_snapshot when you only need text. Hidden elements (display:none, visibility:hid...

Browser Handle Dialog

Handle a dialog

Browser Hover

Hover over element on page

Browser Iframe Click

Click an element inside an iframe. Use browser_snapshot to get iframeRef and element ref.

Browser Iframe Fill

Fill an input field inside an iframe. Use browser_snapshot to get iframeRef and field ref.

Browser Install

Install the browser specified in configuration (chromium, firefox, or webkit). Downloads and sets up the browser if not already installed. This is typ...

Browser Navigate

Navigate to a URL in the browser. Returns navigation result with final URL (after redirects), page title, and status. Use this as the starting point f...

Browser Navigate Back

Go back to the previous page

Browser Network Requests

Returns network requests for the current page with request IDs for detailed inspection

Browser Performance Trace

Start or stop performance tracing to analyze page performance, Core Web Vitals (LCP, FID, CLS), and identify bottlenecks

Browser Press Key

Press a key or key combination on the keyboard. Supports special keys (Enter, Escape, Tab) and modifiers (Control, Shift, Alt, Meta). Optionally focus...

Browser Resize

Resize the browser window

Browser Run Code

Run a Playwright Python code snippet. The code receives 'page' (Playwright Page object) and can perform any page interaction. Use 'return' to return a...

Browser Save As Pdf

Save the current page as a PDF file. Returns base64-encoded PDF if path not provided.

Browser Scroll

Scroll the page by direction/amount, scroll to top/bottom, or scroll a specific element into view. Essential for lazy-loading pages and content below ...

Browser Select Option

Select an option in a dropdown

Browser Set Cookies

Set or delete browser cookies including HttpOnly cookies. Use 'cookies' to add/update cookies (name+value required, domain defaults to current page). ...

Browser Snapshot

Capture accessibility snapshot of the current page, this is better than screenshot

Browser Tabs

List, create, close, or select a browser tab.

Browser Take Screenshot

Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.

Browser Type

Type text into editable element

Browser Wait For

Wait for text to appear or disappear or a specified time to pass

Frequently Asked Questions

What is the Remote Browser MCP server?

Cloud-hosted Chrome browser powered by Steel.dev — zero setup required. Navigate pages, click, type, take screenshots, fill forms, run JavaScript, and inspect network traffic. For localhost access, run: mcpbundles proxy expose <port> It provides 35 tools that AI agents can use through the Model Context Protocol (MCP).

How do I connect Remote Browser to my AI agent?

Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/remote-browser. Authentication is handled automatically.

How many tools does Remote Browser provide?

Remote Browser provides 35 tools that can be called by AI agents, along with a SKILL.md that gives your AI agent domain knowledge about when and how to use them.

What authentication does Remote Browser require?

Remote Browser uses open data APIs — no authentication required.

What is Remote Browser best for?

It is best for zero-install browser automation against public websites or tunnel-exposed local apps, using a cloud-hosted Chrome session.

How is Remote Browser different from Local Browser?

Remote Browser runs Chrome in the cloud and needs a tunnel for localhost. Local Browser runs on the user's machine and reaches localhost directly.

Can it capture screenshots?

Yes. The remote browser can take screenshots and return visual content for agents to inspect during page review and QA workflows.

When does localhost require extra setup?

Because the browser runs in the cloud, localhost URLs need to be exposed through the MCPBundles proxy tunnel before the remote browser can reach them.

Setup Instructions

Connect Remote Browser to any MCP client in minutes

MCP URL
https://mcp.mcpbundles.com/bundle/remote-browser

One-click install:

The link prefills the Add custom connector dialog — you still review the values and click Add, then Connect to complete OAuth.

Or add manually

  1. Open claude.ai → Settings → Connectors.
  2. Click the + button and choose Add custom connector.
  3. Set Name to Remote Browser and paste the MCP URL into Remote MCP server URL.
  4. Click Add. Remote Browser will appear under Not connected — select it and click Connect to complete OAuth.
Name: Remote Browser
Remote MCP server URL: https://mcp.mcpbundles.com/bundle/remote-browser
Authentication: OAuth

Custom connectors at claude.ai require a paid Claude plan (Pro, Max, Team, or Enterprise).

Try Remote Browser now

No API key or third-party login required. Chat with AI and run tools instantly.

Remote Browser MCP Server & Skill — 35 Tools