How to Use the Urlbox MCP in LangChain

Get Visual Data from URLs, Built for LangChain Agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Urlbox MCP to LangChain

Create your Vinkius account to connect Urlbox 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 Urlbox with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Extracting Structured Content via MCP Server

You can build complex pipelines that use the output of one tool to drive another. For example, an agent first uses `get_metadata` on a URL to check its basic details. The subsequent step then takes that validated URL and processes it further using `generate_pdf`, creating a structured document for later analysis. This allows your multi-step reasoning agents to handle the flow from discovery to documentation. You're not just calling tools; you're linking them into an observable chain, which is perfect for sophisticated workflows.

Multi-View Web Auditing with LangChain

Need to see how a page looks across different devices? Your agent can execute a sequence of visual checks. It runs `take_screenshot` for the standard view, then calls `take_mobile_screenshot` to check responsiveness. Finally, it might follow up by running `take_retina_screenshot` to ensure high-resolution assets look right. This sequential approach lets your LangChain agent compare these inputs directly within a single chain execution. You get comprehensive coverage without having to write separate scripts for each view.

Automated PDF Creation with MCP Server

The `generate_pdf` tool turns any given URL into a complete, usable PDF file. This is critical when you need an external record of web content that isn't just raw text. Your LangChain agent can use this to package up research findings or audit reports instantly. This step acts as the final output gate for your chain. Once all the data gathering and processing are done, running `generate_pdf` gives you a single, portable file containing all the visual evidence gathered.

Setup guide

Set up Urlbox 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 Urlbox 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({
    "urlbox-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 Urlbox 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 Urlbox. 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 Urlbox 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 Urlbox MCP in LangChain

LangChain treats the MCP Server's tools as just another callable function. Your agent decides when to run `take_full_page_screenshot` or `get_metadata`. The output from that tool becomes an intermediate piece of data the agent uses for its next decision.

Yes, absolutely. You can chain visual checks together. For instance, you might check `take_screenshot` first, and if the result is bad, prompt another tool call like `get_metadata` to gather more context before failing gracefully.

The server touches URL content and metadata. This includes the raw text retrieved by tools like `generate_pdf`, the visual image data from all screenshot methods, and basic site details gathered via `get_metadata`.

It's built for it. The stateless nature of the MCP Server means you can use your client session to pass results between tool calls, making it ideal for multi-step logic.

The tools support various URL content formats. You just need to ensure the input passed from your chain's previous step is a correctly formatted string that the server can recognize for processing.

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