ZenRows MCP Integration

Connect your AI assistant to ZenRows via MCP to scrape webpages and automate browser interactions on JavaScript-heavy and bot-protected sites.

What is the ZenRows MCP?

The ZenRows MCP (Model Context Protocol) server connects ZenRows’ web scraping and browser automation capabilities directly to MCP-compatible AI tools like Claude, Cursor, or VS Code Copilot. Once configured, your AI assistant can fetch real-time content from any webpage and control a full browser session on your behalf.

It connects to two ZenRows products:

• Universal Scraper API — for fast, single-request scraping with JavaScript rendering, residential proxies, and anti-bot bypass.
• Scraping Browser — for multi-step browser automation through a cloud-hosted browser with built-in anti-bot protection and residential proxies.

What you can do

• Scrape any webpage by describing the task in plain English
• Extract structured data from e-commerce sites, news pages, or search results
• Take screenshots of any page for visual inspection
• Access geo-restricted or bot-protected pages using premium proxies
• Automate multi-step browser workflows: navigate, click, fill forms, scroll, and extract data across pages
• Run JavaScript in a live browser context
• Manage cookies, local storage, and multiple tabs

Before you start

You need:

ZenRows Account

A ZenRows account

ZenRows API Key

Your ZenRows API key

Supported integrations

Tool	Type
Claude Desktop	AI assistant
Claude Code	AI coding assistant
Cursor	AI code editor
Windsurf	AI code editor
VS Code	AI code editor
Zed	AI code editor
JetBrains IDEs	AI code editor

How it works

All integrations use the same MCP server package (@zenrows/mcp) and the same configuration pattern. Each tool has a configuration file where you register MCP servers. Adding ZenRows gives your AI assistant access to the scrape tool for single-request scraping and a full set of browser_* tools for multi-step browser automation.

Once configured, ask your assistant to scrape a page or automate a browser workflow and it handles the request automatically:

Scrape https://scrapingcourse.com/ecommerce/ and list the names and prices of the products.

Open https://www.scrapingcourse.com/ecommerce/ in a browser, type "hoodie" into the search field, press Enter, wait for the results to load, then extract all matching product names and prices.

Tools

The ZenRows MCP exposes two types of tools to your AI assistant.

The scrape tool

The scrape tool fetches a webpage in a single request and returns its content in the format you specify: clean Markdown (default), plain text, raw HTML, a screenshot, or structured JSON. It uses the Universal Scraper API under the hood.

Best for quick data extraction where you don’t need to interact with the page.

Browser tools

The browser_* tools give your AI assistant control of a cloud-hosted browser session powered by the ZenRows Scraping Browser. The browser comes with built-in residential proxies and anti-bot protection.

Use browser tools when you need to:

• Navigate across multiple pages in a single session
• Fill out forms, click buttons, or interact with page elements
• Wait for dynamically loaded content
• Execute JavaScript in the browser context
• Manage cookies, local storage, or multiple tabs

Every browser workflow starts with browser_navigate, which opens a session and returns a session_id. All subsequent browser calls use this session_id. Always call browser_close when done.

Available browser tools

Session

Tool	Description
browser_navigate	Open a browser session and navigate to a URL. Returns a session_id for subsequent calls.
browser_close	Close a browser session and free all associated resources.

Navigation

Tool	Description
browser_go_back	Navigate back in browser history.
browser_go_forward	Navigate forward in browser history.
browser_reload	Reload the current page.

Interaction

Tool	Description
browser_click	Click an element using a CSS selector.
browser_hover	Hover over an element to trigger hover effects.
browser_type	Type text into an input field. Appends to existing content unless clear_first is set.
browser_fill	Clear an input field and set its value.
browser_select_option	Select an option from a <select> dropdown.
browser_check	Check a checkbox or radio button.
browser_uncheck	Uncheck a checkbox.
browser_focus	Move focus to an element.
browser_press_key	Press a keyboard key (e.g. Enter, Tab, Escape, Control+a).
browser_scroll	Scroll the page in a given direction.
browser_drag	Drag an element to a target element.

Extraction

Tool	Description
browser_get_accessibility_tree	Get the page’s accessibility tree as readable text. Call this after browser_navigate to understand page structure.
browser_get_url	Get the current URL.
browser_get_title	Get the page title.
browser_get_text	Get the visible text of an element or the entire page.
browser_get_attribute	Get the value of a specific attribute on an element.
browser_get_html	Get the HTML source of an element or the full page.
browser_query_selector_all	Find all elements matching a CSS selector. Returns text, HTML, and attributes.

Visual

Tool	Description
browser_screenshot	Take a screenshot of the page or a specific element.
browser_generate_pdf	Render the current page as a PDF.

Wait

Tool	Description
browser_wait_for_selector	Wait until an element is stable in the DOM. Set visible=true to require visibility.
browser_wait_for_navigation	Wait for a page navigation. Call this before the action that triggers navigation.
browser_wait	Wait for a fixed duration in milliseconds.

JavaScript

Tool	Description
browser_evaluate	Execute JavaScript in the browser context and return the result.

Cookies

Tool	Description
browser_get_cookies	Get all cookies for the current page.
browser_set_cookies	Set one or more cookies.
browser_clear_cookies	Clear all cookies for the session.

Storage

Tool	Description
browser_local_storage	Read, write, or clear localStorage.

Tabs

Tool	Description
browser_new_tab	Open a new tab. Returns a tab_id.
browser_switch_tab	Switch focus to a different tab.

Batch

Tool	Description
browser_batch	Execute a sequence of browser actions in a single call for better performance.

Scrape vs. browser tools

	scrape	browser_* tools
Best for	Single-page data extraction	Multi-step workflows and interactions
Backed by	Universal Scraper API	Scraping Browser
Session	Stateless, one request per call	Persistent session across multiple calls
Interaction	Limited (via js_instructions)	Full browser control (click, type, scroll, etc.)
Output	Markdown, plain text, HTML, JSON, screenshot, PDF	Text, HTML, screenshots, PDF, JSON, accessibility tree

Troubleshooting

Common issues and solutions

Issue	Cause	Solution
Page content is missing or blank	Page uses JavaScript to load content dynamically	Enable js_render: true in the scrape tool, or use browser_navigate for full browser rendering
403 error or bot detection page	Target site blocks datacenter IPs	Enable premium_proxy: true in the scrape tool. Browser tools use residential proxies automatically
Content is geo-restricted	Site serves different content by region	Enable premium_proxy: true and set proxy_country to the target country code (e.g. US)
Content loads after a delay	Page renders elements asynchronously	Use wait_for with a CSS selector, or wait with a millisecond value. Both require js_render: true. With browser tools, use browser_wait_for_selector
Content only appears after a click or form input	Page requires user interaction before loading data	Use js_instructions with the scrape tool, or use browser tools (browser_click, browser_fill, etc.) for full control
Response contains full page instead of specific fields	No extraction parameters set	Use css_extractor with a JSON selector map, autoparse for structured pages, or outputs for specific data types
Screenshot appears blank	Page loads content dynamically	Enable js_render: true alongside the screenshot parameter, or use browser_screenshot after waiting for content
The scrape tool is unavailable in your AI assistant	Configuration not loaded yet	Restart your AI tool after saving the configuration file. For Claude Desktop, fully quit and reopen the application
API key is not recognized	Key not replaced in configuration	Confirm YOUR_ZENROWS_API_KEY has been replaced with your actual key from the ZenRows dashboard. The value must have no extra spaces or surrounding quotation marks
Browser session timed out	Session exceeded its TTL	Start a new session with browser_navigate. Keep sessions short and close them when done

Example prompts

Once you configure the ZenRows MCP, describe the task to your AI assistant and it handles the scraping automatically.

Scrape tool examples

Fetch https://www.scrapingcourse.com/javascript-rendering/. It uses React, so enable JavaScript rendering.

Get the top 5 products from https://www.scrapingcourse.com/ecommerce/ and extract just the names and prices.

Take a full-page screenshot of https://news.ycombinator.com.

Scrape https://www.scrapingcourse.com/antibot-bypass — it's blocking requests. Use Premium Proxies.

Browser tool examples

Open https://www.scrapingcourse.com/ecommerce/ in a browser, type "hoodie" into the search field, press Enter, wait for the results to load, then extract all matching product names and prices.

Navigate to https://scrapingcourse.com/ecommerce/, click on the first product, extract its full description and price, then go back and do the same for the second product.

Open https://news.ycombinator.com in a browser, scroll down to load more stories, then extract all the headlines and links.

Related resources

• ZenRows Universal Scraper API Reference
• ZenRows Scraping Browser Introduction
• ZenRows Dashboard
• GitHub Repository
• NPM Package

Contributing

The ZenRows MCP server is open source. If you want to modify the server, fix a bug, or suggest an improvement, clone the repository and run it locally:

git clone https://github.com/ZenRows/zenrows-mcp
cd zenrows-mcp
npm install
cp .env.example .env   # Add your API key
npm run dev            # Run with .env loaded (requires Node.js 20.6+)
npm run build          # Compile to dist/
npm run inspect        # Open the MCP inspector UI

Pull requests and issues are welcome on the GitHub repository.