Use ZenRows with your AI.
Connect your account once and let the AI you already use work with it, without building another integration. Scrape HTML, bypass anti-bots, and extract structured data using ZenRows' advanced proxy and browser network.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Complete set · 10 capabilities
The complete ZenRows capability set.
These are the exact actions your AI can choose when you ask it to work with ZenRows.
01-04
4 capabilities in this set.
Part of 10 available through ZenRows.
- 01
Get screenshot
Generates a URL that returns a screenshot of the target page
- 02
Scrape premium
Sets premium_proxy=true for higher anonymity. Scrape using ZenRows premium residential proxies
- 03
Scrape autoparse
Scrape with automatic structured data extraction
- 04
Scrape custom
G. wait, css_extractor, session_id). Execute a scrape using advanced custom parameters
05-07
3 capabilities in this set.
Part of 10 available through ZenRows.
- 05
Scrape geo
G. "us", "gb") for localized content. Scrape using a proxy from a specific country
- 06
Scrape HTML
ZenRows automatically rotates proxies and handles CAPTCHAs. Scrape raw HTML using ZenRows anti-bot proxy pool
- 07
Scrape markdown
Automatically removes boilerplate like navigation and ads. Scrape and convert page content to clean Markdown
08-10
3 capabilities in this set.
Part of 10 available through ZenRows.
- 08
Scrape wait
G. "#results") to wait for before capturing the HTML. Scrape with JS render waiting for a specific CSS selector
- 09
Scrape antibot
Enables js_render and antibot=true. Scrape with full anti-bot bypass for heavily protected sites
- 10
Scrape js
Enables js_render=true. Slower and more expensive than static scraping. Scrape JS-rendered HTML using ZenRows headless browser
Observed, not estimated
918ms average. Fast in production.
ZenRows is checked daily against the live service.
- Fastest day
- 747ms
- Slowest day
- 1064ms
- 14-day trend
- Slowing+11%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of ZenRows, so you can see the experience inside your AI.
It does not authenticate your account with ZenRows. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
ZenRows Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_jR8Ah5rxvahJ5kVneMnPRI8kVBd5MZWswd5Nogxu/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — ZenRows capabilities are ready to use.
{
"mcpServers": {
"zenrows-mcp": {
"url": "https://edge.vinkius.com/vk_preview_jR8Ah5rxvahJ5kVneMnPRI8kVBd5MZWswd5Nogxu/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
FAQ
Questions ZenRows owners ask.
- 01
Can ZenRows bypass Cloudflare or other aggressive bot protections?
Yes. Using the scrape_antibot capability, ZenRows activates specialized technology to bypass Cloudflare, DataDome, and other advanced bot detection systems, ensuring you can access the content you need through chat.
- 02
How do I get clean Markdown from a website for my AI agent?
You can use the scrape_markdown capability. ZenRows will retrieve the page and automatically convert the content into structured Markdown, removing ads and navigation headers to provide a clean input for LLMs.
- 03
Can I see what a dynamic page looks like before extracting data?
Absolutely. Use the get_screenshot capability to retrieve a direct link to an image file representing the fully rendered target page, helping you verify that JavaScript content is correctly displayed.
Explore
More in Developer Tools
Firecrawl AI Connector
Crawl and scrape entire websites into clean LLM-ready markdown with a single API call that handles JavaScript
ViewScrapingBee AI Connector
Powerful web scraping with JS rendering, premium proxies, and AI-powered data extraction directly from your AI
ViewFirecrawl AI Connector
Crawl and scrape entire websites into clean LLM-ready markdown with a single API call that handles JavaScript
ViewFirecrawl AI Connector
Turn any website into clean, LLM-ready Markdown with a single API call — scrape, crawl, search, and map the en
View
Suggestions
Spider AI Connector
High-performance Rust-powered web scraping and crawling — scrape, crawl, and search up to 100K+ pages/second w
ViewMarkdown Semantic Chunker AI Connector
A deterministic engine for splitting Markdown text into semantically coherent chunks based on header hierarchy
ViewLLM JSON Extractor AI Connector
Isolates valid JSON objects from messy LLM text outputs.
ViewMarkdown Semantic Chunker AI Connector
A deterministic engine for splitting Markdown text into semantically coherent chunks based on header hierarchy
View
