4,500+ servers built on MCP Fusion
Vinkius
Nuvei logo
Vinkius
LangChain logo

How to Use the Nuvei MCP in LangChain

Connect your LangChain agents directly to Nuvei to run secure tokenization and settle payments inside your runtime chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Nuvei MCP on Cursor AI Code Editor MCP Client Nuvei MCP on Claude Desktop App MCP Integration Nuvei MCP on OpenAI Agents SDK MCP Compatible Nuvei MCP on Visual Studio Code MCP Extension Client Nuvei MCP on GitHub Copilot AI Agent MCP Integration Nuvei MCP on Google Gemini AI MCP Integration Nuvei MCP on Lovable AI Development MCP Client Nuvei MCP on Mistral AI Agents MCP Compatible Nuvei MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
LangChain

Connect Nuvei MCP to LangChain

Create your Vinkius account to connect Nuvei 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

Chain tokenization and charges in LangChain

The `create_card_token` tool converts raw payment details into secure tokens directly within your LangChain execution steps. Your agent chains this token output into `create_payment` to charge the customer without exposing raw card numbers to your logs. We pass the resulting transaction status down the chain to trigger subsequent fulfillment steps automatically. Using this MCP Server within LangGraph allows your multi-step pipelines to handle complex payment logic. If a transaction fails, the chain routes to `get_payment` to verify the state before attempting a retry or logging a failure.

Automate settlement and voids via LangChain agents

The `capture_payment` tool registers previously authorized transactions inside your LangChain agent runtimes. The agent inspects your order database, finds pending holds, and executes captures or triggers `void_payment` to release the funds. This setup removes the need for manual billing intervention by letting your agent make decisions based on live API responses. You get full visibility of these multi-step payment operations through LangSmith tracing when using an MCP client. Every call to `refund_payment` or payment lookup shows up with exact latency and inputs, giving you a clear audit trail of your automated financial operations.

Manage vaulted tokens inside LangChain pipelines

The `update_token` tool modifies expiry dates and card metadata inside your LangChain customer management workflows. When a user updates their billing profile, your agent calls this tool to refresh the vaulted token without asking for the full card number again. For customers closing accounts, the agent calls `delete_token` to immediately stop recurring charges. This keeps your token database clean and reduces compliance overhead since your LangChain pipeline handles the lifecycle events directly.

Setup guide

Set up Nuvei MCP in LangChain

Prerequisites

  • Python 3.10+ installed
  • langchain-mcp-adapters + langgraph packages
  • Active Vinkius subscription with a valid endpoint token
  1. 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. 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. 3

    Create a ReAct agent

    Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Nuvei tool calls through the MCP protocol.

  4. 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({
    "nuvei-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 Nuvei transactions"
    })
    print(result["messages"][-1].content)

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Nuvei. 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.

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 Nuvei MCP in LangChain

Install langchain-mcp-adapters and use the MultiServerMCPClient to point to the Vinkius endpoint. This registers all ten payment tools, allowing your LangChain agents to call create_payment or get_token directly during a run.
Yes. Your agent analyzes the refund request, calls get_payment to verify the original capture, and then executes refund_payment with the specific partial amount.
LangChain is stateless by default, but you can use client.session() to maintain context across tool calls. This is useful when your agent needs to call get_token and then instantly run update_token on the same reference.
The step returns the API failure message to the agent. You can configure your LangChain routing to catch these errors and trigger void_payment or log the transaction ID for manual review.
This MCP integration ensures raw credit card details are instantly sent to Nuvei via create_card_token and never touch your local logs or LangChain context. The server only returns secure payment tokens, keeping your runtime environment entirely out of PCI-DSS scope.

Start using the Nuvei MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 10 tools

We've already built the connector for Nuvei. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.