How to Use the Worldpay MCP in LangChain

Q: How does LangChain use Worldpay for token management?

You call createreusabletoken first, which generates a safe payment token from sensitive card data. Your agent then uses that resulting token as the input when creating a new order via createpaymentorder. This keeps your process secure and verifiable.

Q: Can LangChain list all Worldpay settlements?

Yes, you can use listpaymentsettlements to get the full history of funds that have been settled into your account. You'll see a clear record of every movement using this MCP tool.

Q: What data does Worldpay touch when LangChain handles refunds?

The refundpaymentorder tool requires two pieces of data: the specific order code and the precise amount you intend to refund. Your agent manages this input flow.

Q: What is the typical workflow for Worldpay with LangChain?

A common flow is checking API health with getapihealth, then fetching order details using getorderdetails, and finally performing a refund if necessary.

Q: If I need to verify webhook endpoints, how does Worldpay integrate with LangChain?

You use the dedicated tool listwebhookendpoints. This lets your agent read all registered notification endpoints without needing direct manual access or complex setup.

Build complex payment logic with LangChain and Worldpay.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Worldpay MCP to LangChain

Create your Vinkius account to connect Worldpay 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 Worldpay with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step Payment Processing for LangChain

Start by checking the API status using `get_api_health`. Then, you can chain that check directly into retrieving specific data. For instance, after confirming the Worldpay connection is live, your agent immediately calls `get_order_details` to fetch all relevant order information. This ability lets your ReAct agents build multi-step reasoning pipelines. You might start by listing settlement funds with `list_payment_settlements`, and the output of that list becomes the input for an agent deciding if a refund is warranted using `refund_payment_order`.

Managing Payment Tokens with MCP Server

Need to handle sensitive card data? Use `create_reusable_token` first. This tool takes raw card details and outputs a safe, reusable token. Once you have that token, your chain doesn't need the raw data again. You can pass this secure token directly into `create_payment_order`, ensuring compliance while still performing necessary actions like generating a new payment order.

Auditing Worldpay Transactions in LangChain

When auditing transactions, you'll often need to check multiple data points. Your chain can first call `get_order_details` for an order code. Next, if the payment was completed, you can follow up by calling `list_webhook_endpoints`. This sequence confirms not only that the order exists but also how Worldpay is configured to notify external systems about its status.

Setup guide

Set up Worldpay 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 Worldpay 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({
    "worldpay-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 Worldpay 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 Worldpay. 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 Worldpay 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 Worldpay MCP in LangChain

You call `create_reusable_token` first, which generates a safe payment token from sensitive card data. Your agent then uses that resulting token as the input when creating a new order via `create_payment_order`. This keeps your process secure and verifiable.

Yes, you can use `list_payment_settlements` to get the full history of funds that have been settled into your account. You'll see a clear record of every movement using this MCP tool.

The `refund_payment_order` tool requires two pieces of data: the specific order code and the precise amount you intend to refund. Your agent manages this input flow.

A common flow is checking API health with `get_api_health`, then fetching order details using `get_order_details`, and finally performing a refund if necessary.

You use the dedicated tool `list_webhook_endpoints`. This lets your agent read all registered notification endpoints without needing direct manual access or complex setup.

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