How to Use the ZenRows MCP in LangChain

Q: How does LangChain use ZenRows to get screenshots?

You call getscreenshot when the agent needs visual proof or an overview of a page's state. The tool returns a URL that lets your client view exactly what the target browser saw at that moment.

Q: What if I need high anonymity for my LangChain workflow?

Use scrapepremium to set premium proxy usage. This gives your MCP Server higher levels of anonymity, which is critical when building sensitive or large-scale agents that touch protected data.

Q: How do I handle timing issues in my LangChain agent?

The scrapewait tool lets you pause the scraping process until a specific element appears, identified by a CSS selector. This prevents the agent from trying to read content that hasn't loaded yet.

Build multi-step reasoning agents using the ZenRows MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ZenRows MCP to LangChain

Create your Vinkius account to connect ZenRows to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup ZenRows with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Bypass anti-bot measures in your LangChain agent.

The `scrape_antibot` tool lets your agent scrape heavily protected sites. This is crucial when a key piece of data sits behind multiple layers of bot detection. Your multi-step reasoning pipeline can call this tool to gather the initial, difficult-to-get payload. The output then feeds directly into the next step, allowing the agent to proceed with confidence.

Structure scraped data using the ZenRows MCP Server.

Don't just get raw HTML; use `scrape_markdown` to clean up messy web content. This tool strips out all the boilerplate—like navigation bars and ads—so your agent only sees the usable text. This structured output is ideal for feeding into an LLM prompt because it removes noise, keeping the context window focused on what matters.

Execute complex scraping logic in LangChain.

When a page requires dynamic rendering (like content loaded by JavaScript), call `scrape_js`. This method enables your agent to act like a real browser, executing the necessary scripts. If you need more control, `scrape_custom` lets you define specific CSS selectors or even manage session IDs for highly targeted data extraction within a complex chain.

Setup guide

Set up ZenRows MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes ZenRows tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "zenrows-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent ZenRows transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by ZenRows. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect ZenRows now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about ZenRows MCP in LangChain

You call `get_screenshot` when the agent needs visual proof or an overview of a page's state. The tool returns a URL that lets your client view exactly what the target browser saw at that moment.

Yes. To scrape content localized to a specific region, pass country codes like 'us' or 'gb' into `scrape_geo`. This lets your agent target the right market immediately.

Absolutely. The MCP Server handles proxy rotation and CAPTCHA challenges automatically via `scrape_html`. Your LangChain agent doesn't need to worry about getting blocked; the tool manages the underlying network complexity.

Use `scrape_premium` to set premium proxy usage. This gives your MCP Server higher levels of anonymity, which is critical when building sensitive or large-scale agents that touch protected data.

The `scrape_wait` tool lets you pause the scraping process until a specific element appears, identified by a CSS selector. This prevents the agent from trying to read content that hasn't loaded yet.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript