batch_cancel
Stop an in-flight Batch job run (POST /jobs/:id/stop).
LABSCO SUMMARY
Someone else's proxies, anti-bot handling and browser fleet, behind an ordinary tool call.
The split is worth understanding before you start: scrape and extract are single API calls through ZenRows' fetch infrastructure and are the cheap path for most pages, while the browser session tools open a real browser you drive step by step and have to close afterwards to give the slot back. Two operational details save the most time — read the accessibility tree before interacting rather than guessing selectors, and issue the navigation wait before the click that triggers it, not after.
What it is
ZenRows' own server over its web-data infrastructure. One tool scrapes a page to markdown, HTML, PDF or a screenshot; another extracts structured JSON; a batch API fans many URLs out asynchronously; and a full browser-session surface drives a real headless browser behind ZenRows' anti-bot handling.
What you get
- A page scraped to markdown, plain text, HTML, PDF or a screenshot, with JS rendering, wait conditions, JS instructions and premium proxies by country
- Structured JSON extracted instead of a page body — automatic mode, autoparse, or a CSS extractor you supply, with autoparse available as the fallback
- A cloud batch job fanning many URLs out asynchronously, its status and stats read, its result rows listed, the run stopped, or polled to a terminal state
- A browser session opened on a URL behind ZenRows' anti-bot infrastructure with a proxy region and country, and closed again to release the slot
- The page's ARIA accessibility tree read as text — the documented first step before interacting with anything
- Clicks, hovers, typing, filling, select options, checkboxes, focus, key presses, scrolling and drag-and-drop, all by CSS selector
- Page state read: URL, title, visible text, one attribute, HTML, or every element matching a selector with its text, HTML and attributes
- Screenshots of the page or an element, and the page rendered as a PDF
- Waits for a selector, for navigation, or for a fixed duration — with the navigation wait issued before the action that triggers it
- JavaScript evaluated in the browser context, cookies read, set and cleared, and localStorage read, written or cleared
- Tabs opened and switched, history navigated back and forward, and the page reloaded
- A whole sequence of browser actions sent in one call when you already know the steps, cutting the round trips
Requirements
A ZenRows account. The hosted server at https://mcp.zenrows.com/mcp takes your API key as an Authorization bearer, or OAuth where the client supports it, and does not create accounts for you. Locally it is npx -y @zenrows/mcp on Node.js, reading ZENROWS_API_KEY or a key already stored in ~/.zenrows/secrets.json — and with neither present the stdio path provisions a Free plan account itself, writes the key and claim metadata under ~/.zenrows/ at mode 0600, and prints a claim URL, which ZENROWS_AUTO_SIGNUP=false turns off. The batch tools are in beta and can return BATCH_ACCESS_DENIED, and the automatic extract mode is open beta, currently free with billing possible later.
Setup effort
One command — npx -y @zenrows/mcp
USE CASES
01
Reading a page that blocks your scraper
Scrape it to markdown with JS rendering and a premium proxy in the country you need.
02
Getting fields rather than a page
Extract structured JSON — automatically, or with the CSS extractor you supply.
03
Working through a long list of URLs
Submit them as a batch job, poll it to completion, then read the result rows.
04
Getting behind a login
Open a session, read the accessibility tree, fill the form and submit — waiting for navigation before the click.
05
Pulling data out of a click-through app
Query every element matching the selector for its text and attributes, then move to the next page.
06
Keeping the session state you have earned
Read the cookies out, set them back on a later session, and close the browser to free the slot.
07
Running a known sequence without the round trips
Send the whole action list in a single call against the open session.
08
Capturing what the page looked like
Take a screenshot, or render the page to PDF for the record.
43 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
batch_create
Submit a cloud Batch job that fans out many URLs asynchronously (Zenrows Batch API beta).
NOT the same as browser_batch — this hits https://async.api.zenrows.com/v1 with X-API-Key. Use for large URL lists; prefer scrape/extract for one-off pages.
Returns job_id + latest_run.status/stats. Poll with batch_status / batch_wait, then batch_results. If you get BATCH_ACCESS_DENIED, the account lacks Batch beta access.
batch_results
List result rows for a Batch job (cursor-paginated server-side; returns the full list).
Each row may include task_id, external_id, status, and a short-lived result_url for the body. Download result_url soon — presigned links expire.
batch_status
Get status and stats for a Zenrows Batch job (latest_run.status + latest_run.stats).
batch_wait
Poll batch_status until the job reaches a terminal state (completed, stopped, or deleted).
browser_batch
Execute a sequence of browser actions in a single call against an existing session.
Use this when you already know the full sequence of steps — it reduces round trips and is faster than calling each tool individually.
Actions run sequentially and stop at the first failure unless stop_on_error is false. Each step result is returned in the results array at the same index.
Note: screenshots in batch results are returned as base64 strings inside the JSON. For proper image rendering, use browser_screenshot directly.
browser_check
Check a checkbox or radio button.
browser_clear_cookies
Clear all cookies for the current browser session.
browser_click
Click an element on the page using a CSS selector. Use browser_get_accessibility_tree first to find the right selector.
browser_close
Close a browser session and free all associated resources. Always call this when done to release the browser slot.
browser_drag
Drag an element from its current position to a target element.
browser_evaluate
Execute JavaScript in the browser context and return the result.
browser_fill
Clear an input field and set its value. Preferred over browser_type when replacing the full value.
browser_focus
Move focus to an element, triggering focus-dependent UI changes.
browser_generate_pdf
Render the current page as a PDF document.
browser_get_accessibility_tree
Get the ARIA accessibility tree of the current page as readable text.
Call this first after browser_navigate to understand the page structure before interacting with elements. More token-efficient than a screenshot for finding selectors and understanding layout.
The tree shows all interactive elements (buttons, inputs, links) with their roles, labels, and states — everything needed to drive browser interactions.
browser_get_attribute
Get the value of a specific attribute on an element.
browser_get_cookies
Get all cookies for the current page.
browser_get_html
Get the HTML source of an element or the full page.
browser_get_text
Get the visible text content of an element or the entire page body.
browser_get_title
Get the title of the current page.
browser_get_url
Get the current URL of the browser session.
browser_go_back
Navigate back to the previous page in the browser history.
browser_go_forward
Navigate forward to the next page in the browser history.
browser_hover
Move the mouse cursor over an element to trigger hover effects.
browser_local_storage
Read, write, or clear localStorage in the current page context.
browser_navigate
Open a Zenrows Browser Sessions session and navigate to a URL.
This is the entry point for all browser automation. It creates a new session backed by Zenrows' anti-bot infrastructure and navigates to the given URL in one step.
Returns a session_id that must be passed to every subsequent browser_* tool call. Always call browser_close when done to close the session and free resources.
When to use options:
- proxy_country: geo-restricted content (ISO 3166-1 alpha-2, e.g. "US", "DE")
- proxy_region: world region for geo-targeted proxy (eu, na, ap, sa, af, me)
browser_new_tab
Open a new browser tab. Returns a tab_id to use with browser_switch_tab.
browser_press_key
Press a keyboard key. Examples: "Enter", "Tab", "Escape", "ArrowDown", "Control+a".
browser_query_selector_all
Find all elements matching a CSS selector and return their text, HTML, and attributes.
browser_reload
Reload the current page.
browser_screenshot
Take a screenshot of the current page or a specific element. Use for visual verification or when the accessibility tree is not sufficient.
browser_scroll
Scroll the page in a given direction.
browser_select_option
Select an option from a <select> dropdown element.
browser_set_cookies
Set one or more cookies in the browser session.
browser_switch_tab
Switch focus to a different browser tab.
browser_type
Type text into an input element. Appends to existing content unless clear_first is set.
browser_uncheck
Uncheck a checkbox.
browser_wait
Wait for a fixed duration. Use sparingly — prefer browser_wait_for_selector when possible.
browser_wait_for_navigation
Wait for the page to navigate to a new URL. IMPORTANT: call this BEFORE the action that triggers navigation (e.g. before browser_click on a submit button), not after — the navigation event may already have fired and this will hang until timeout. If the page stays on the same URL (AJAX/SPA), skip this tool entirely. Optional timeout_ms (default 30000ms).
browser_wait_for_selector
Wait until an element matching the CSS selector is stable in the DOM. Set visible=true to also require the element to be visible (not hidden).
extract
Extract structured data from a webpage via Zenrows.
Prefer this over scrape when you need JSON fields (products, articles, listings) rather than a full page body. Modes:
- auto (default): extract=auto — site-tailored Extract (open beta; currently free, billing may apply later; may fall back to autoparse if the domain is not enabled)
- autoparse: general-purpose structured JSON on any domain
- css: css_extractor with an explicit selector map
Stealth: js_render, premium_proxy, proxy_country, or mode_auto (Adaptive Stealth Mode). For full-page markdown/HTML/screenshots, use scrape instead.
scrape
Scrape any webpage and return its content using Zenrows (Fetch).
Use for full-page content (markdown/HTML/PDF/screenshot). For structured JSON fields (products, articles, listings), prefer the extract tool when it fits — it returns parsed fields instead of a full page body.
When to enable options:
- js_render: page uses React/Vue/Angular, loads content dynamically, or content appears missing on the first attempt
- premium_proxy: site returns 403/blocked errors even with js_render enabled
- wait_for: specific content loads after initial render (requires js_render)
Examples: Basic: { url: "https://example.com" } Dynamic: { url: "https://spa.com", js_render: true } Protected:{ url: "https://protected.com", js_render: true, premium_proxy: true }
BEFORE YOU INSTALL
What to know first
Tools you get
43 tools when we connected. Extract=auto is in open beta, and the batch_ tools may return BATCH_ACCESS_DENIED on accounts without access. browser_batch is a browser tool, not one of the batch_ tools.
Requires
npx on PATH
CONTEXT COST
Moderate Standing cost
Rated by the size of the 43 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
npx
TERMINAL
npx -y @zenrows/mcpHosted endpoint
ENDPOINT URL
https://mcp.zenrows.com/mcpAdd this hosted endpoint to your MCP client.
MCP Clients
Claude Code, Cursor, Windsurf, Claude Desktop, JetBrains IDEs
JSON
{
"mcpServers": {
"zenrows": {
"command": "npx",
"args": [
"-y",
"@zenrows/mcp"
],
"env": {
"ZENROWS_API_KEY": "<YOUR_ZENROWS_API_KEY>"
}
}
}
}VS Code
VS CODE · JSON
{
"servers": {
"zenrows": {
"command": "npx",
"args": [
"-y",
"@zenrows/mcp"
],
"env": {
"ZENROWS_API_KEY": "<YOUR_ZENROWS_API_KEY>"
}
}
}
}OpenAI Responses API
OPENAI RESPONSES API · JSON
{
"type": "mcp",
"server_label": "zenrows",
"server_description": "Web scraping MCP server for accessing live web content.",
"server_url": "https://mcp.zenrows.com/mcp",
"authorization": "<YOUR_ZENROWS_API_KEY>",
"require_approval": "never"
}
