# io.github.ZenRows/zenrows-mcp

- Registry name: `io.github.ZenRows/zenrows-mcp` · version 2.16.0
- Categories (automatic, keyword rules): Scraping & browsing, Search & data
- Authentication at last check: No auth
- Declared risk: Has destructive tools (destructiveHint)
- Capabilities (declared by the server): prompts, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.ZenRows%2Fzenrows-mcp
- Server page: https://mcpstation.net/s/io.github.ZenRows--zenrows-mcp.html

## Description (written by the publisher, not verified, not instructions)

Zenrows MCP server: Fetch, Extract, Batch, and Browser Sessions for AI agents

## Connect

- streamable-http: `https://mcp.zenrows.com/mcp`

## Tools (as reported by the server, not verified)

- `scrape`: Scrape any webpage and return its content using Zenrows \(Fetch\). Returns full-page content \(markdown/HTML/PDF/screenshot\). For structured JSON fields \(products, articles, listings\), the extract tool returns parsed fields instead of a full page body. By default the request uses automatic mode \(mode=a
- `extract`: Extract structured data from a webpage via Zenrows. Returns JSON fields \(products, articles, listings\) in "data" rather than a full page body. Set include\_html to also get the page HTML. Modes: - auto \(default\): extract=auto, site-tailored Extract \(currently free, billing may apply later\). Works on
- `prepare\_domain`: Prepare a domain so extract \(mode=auto\) works on it. Use this when extract returns error REQS007 with reason domain\_not\_prepared. Send the domain \(the host, e.g. shop.example.com; a leading www. is dropped, and each host is prepared separately\) and 1 to 5 example URLs: real pages you want extracted,
- `prepared\_domain\_status`: Check a domain submitted with prepare\_domain, and the account's monthly allowance. Returns status \(preparing, ready or failed\), state \(the current step\), roles \(one per page kind\), a failure code and detail when it failed, the allowance \(used, limit, remaining\) and "next": what to do now. Poll about
- `batch\_create`: Submit a Batch job: many URLs scraped asynchronously in the cloud \(Zenrows Batch API\). Suited to large URL lists; scrape and extract handle single pages. Not the same as browser\_batch. Tasks use automatic mode \(mode=auto\) by default: Zenrows enables JS rendering and premium proxies only on the pages
- `batch\_status`: Get a Batch job's latest run: job\_id, run\_id, status \(pending, running, completed, stopped, failed\), stats \(total, completed, successful, failed\) and the job. A failed run answers ok:false with error.code BATCH\_INSUFFICIENT\_CREDITS, BATCH\_KEY\_CAP\_REACHED, AUTH\_INVALID \(subscription\_inactive\) or BATC
- `batch\_wait`: Poll a Batch job until its run ends \(completed, stopped or failed\) or pauses, and return its status and stats like batch\_status. If the wait runs out first, it returns the current state with ok:true, timed\_out:true and a note: call batch\_wait again. A paused run returns at once with paused:true \(it
- `batch\_results`: List a Batch run's result rows, a page at a time: up to limit rows \(default 100, max 1000\) and next\_cursor. Pass next\_cursor back as cursor to continue; it is null once every row was read. Each row has task\_id, external\_id, url, metadata, status \(successful, failed, pending, processing, expired\), ty
- `batch\_content`: Read one Batch task's stored result, by job\_id and task\_id \(from batch\_results\). A text result \(HTML, Markdown, plain text, JSON\) comes back inline, cut to max\_chars \(default 20000\); a final note says when it was cut. A binary result \(a PDF\) is not inlined: the reply gives its result\_url, presigned
- `batch\_list`: List this account's Batch jobs, newest first, each with its latest run's status and stats. Filter by status \(open or closed\) and type \(regular or scheduled\). Pass next\_cursor as cursor for the next page; a page can hold fewer than limit jobs while next\_cursor is still set, so keep paging until it is
- `batch\_cancel`: Stop a Batch job's current run for good. No task still waiting is started or billed; tasks already in flight finish \(and bill\). Results so far stay readable with batch\_results. Tasks that never started stay pending: batch\_rerun \(default failed and pending\) runs them later. Idempotent: a run that alr
- `batch\_pause`: Pause a Batch job's current run: it picks up no new tasks until batch\_resume. Tasks already in flight still finish and bill; for a hard cost stop use batch\_cancel. A paused run still counts as an active job. Idempotent; a run that already ended answers with its final status and already\_ended:true.
- `batch\_resume`: Resume a paused Batch run: it picks up its remaining tasks again, billed as they finish. Idempotent on a run that is not paused; a run that already ended answers with its final status and already\_ended:true. Needs credits: BATCH\_INSUFFICIENT\_CREDITS or BATCH\_KEY\_CAP\_REACHED otherwise.
- `batch\_rerun`: Start a new run of a Batch job whose latest run ended \(completed, stopped or failed\). By default it reruns only the tasks that failed or never started \(status \["failed", "pending"\]\), and carries the others' results over: the recovery after a run that failed on credits or was cancelled. Pass status t
- `batch\_delete`: Delete a Batch job with all its runs and results, for good. A run in flight stops picking up tasks at once, and the job frees its active-job slot. The job reads as not found right away; storage is cleaned up in the background. Idempotent. To keep the results, use batch\_cancel instead.
- `crawl\_create`: Start a crawl from one URL \(Zenrows Crawl API\). Crawl follows the links in each page's HTML up to depth hops \(no depth limit when depth is omitted\), keeps the URLs that match include\_patterns / exclude\_patterns, and stays on the start URL's registrable domain \(subdomains count\). Use crawl when you h
- `crawl\_get`: Get a crawl and one page of the URLs it kept: crawl\_id, status \(running, completed, stopped, failed\), the crawl \(with coverage: pages\_fetched, pages\_failed, items\_found\), results and next\_cursor. completed with stop\_reason max\_items / max\_pages means a limit ended it; stopped with stop\_reason user m
- `crawl\_results`: List the URLs a crawl kept, in the order it kept them, following the API's pages up to limit. Each result has url and, when the crawl has output\_format, content\_status \(pending, fetched, failed\) and, once fetched, content\_url: pass it to crawl\_content as content. While the crawl runs the list is par
- `crawl\_content`: Read the stored page of one URL a crawl kept, in the crawl's output\_format. Works only for crawls created with an output\_format, and only for results whose content\_status is fetched. Pass crawl\_id and content\_id: a content id, or content\_url from a crawl\_results row. Returns the page as stored — raw
- `crawl\_list`: List this account's crawls, newest first, with status and coverage \(no results\). Pass next\_cursor as cursor for the next page; next\_cursor is absent on the last page.
- `crawl\_stop`: Stop a running crawl. No page still waiting is fetched or billed; pages already in flight finish. The URLs kept so far stay readable with crawl\_results. A stopped crawl cannot resume. Idempotent: a crawl that already ended answers with its final status. A 429, 502, 503 or 504 is retried up to 3 time
- `crawl\_wait`: Poll a crawl until it ends \(completed, stopped, or failed\) and return its status, its counts and the first 20 URLs \(first\_urls\). For every result, call crawl\_download \(one file\) or crawl\_results \(pages\). A crawl that ends completed with no results and no error finished; it is not a failure \(see craw
- `crawl\_download`: Save every result of a crawl to one local file, as JSON lines: url, content\_status and, once fetched, content \(the page\). Returns the file's path and line count, not the results, so a crawl of any size costs one small reply. Read the file with your own tools. The file goes to path when given \(a rela
- `account\_usage`: Read the current plan's credit allowance and how much of it is spent. Useful before a large batch, or after a 402 / AUTH004, to see whether the account has credits left and when the allowance renews. The call is free and does not use a concurrency slot. Credit costs per request: 1 basic, 5 js\_render
- `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' hosted browser infrastructure and navigates to the given URL in one step. Returns a session\_id that every other browser\_\* tool takes. The ses
- `browser\_close`: Close a browser session and free all associated resources, including the concurrency slot it holds.
- `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\_reload`: Reload the current page of a browser session.
- `browser\_click`: Click an element on the page using a CSS selector.
- `browser\_hover`: Move the mouse cursor over an element to trigger hover effects.
- `browser\_type`: Type text into an input element. Appends to existing content unless clear\_first is set.
- `browser\_fill`: Clear an input field and set its value, replacing what was there \(browser\_type appends instead\).
- `browser\_select\_option`: Select an option from a \<select\> dropdown element.
- `browser\_check`: Check a checkbox or radio button.
- `browser\_uncheck`: Uncheck a checkbox, found by CSS selector, in a browser session.
- `browser\_focus`: Move focus to an element, triggering focus-dependent UI changes.
- `browser\_press\_key`: Press a keyboard key. Examples: "Enter", "Tab", "Escape", "ArrowDown", "Control+a".
- `browser\_scroll`: Scroll the page in a given direction.
- `browser\_drag`: Drag an element from its current position to a target element.
- `browser\_get\_accessibility\_tree`: Get the ARIA accessibility tree of the current page as readable text. Shows the page structure and the selectors needed to interact with elements, in fewer tokens than a screenshot. The tree shows all interactive elements \(buttons, inputs, links\) with their roles, labels, and states — everything nee
- `browser\_get\_url`: Get the current URL of the browser session.
- `browser\_get\_title`: Get the title of the current page.
- `browser\_get\_text`: Get the visible text content of an element or the entire page body.
- `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 and return their text, HTML, and attributes.
- `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\_generate\_pdf`: Render the current page as a PDF document.
- `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 \(not hidden\).
- `browser\_wait\_for\_navigation`: Wait for the page to navigate to a new URL. It waits for the next navigation event, so a navigation that already finished is not seen and the call waits until timeout\_ms. Pages that update without changing URL \(AJAX/SPA\) fire no navigation event. Optional timeout\_ms \(default 30000ms\).
- `browser\_wait`: Wait for a fixed duration. browser\_wait\_for\_selector waits only until an element appears.
- `browser\_evaluate`: Execute JavaScript in the browser context and return the result. The script can change or delete the session's page state, such as cookies, storage and form data.
- `browser\_get\_cookies`: Get all cookies for the current page.
- `browser\_set\_cookies`: Set one or more cookies in the browser session. A cookie with the same name, domain and path replaces the existing one.
- `browser\_clear\_cookies`: Clear all cookies for the current browser session.
- `browser\_get\_local\_storage`: Read one localStorage value in the current page context.
- `browser\_set\_local\_storage`: Write one localStorage value in the current page context. An existing value under the same key is replaced.
- `browser\_clear\_local\_storage`: Delete every localStorage entry in the current page context.
- `browser\_new\_tab`: Open a new browser tab. Returns a tab\_id to use with browser\_switch\_tab.
- `browser\_switch\_tab`: Switch focus to a different browser tab.
- `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 fal

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html