How to Use the Mastercard MCP in LangChain

Q: How do I chain the Mastercard binlookup and validateaccount tools in LangChain?

You'd have your agent call binlookup first. Then, you'd configure the agent's prompt to use the card type information from that output to decide whether to proceed with validateaccount. The tools themselves are independent, but the agent's logic connects them.

Build financial logic chains that actually work, powered by Mastercard data and your LangChain agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mastercard MCP to LangChain

Create your Vinkius account to connect Mastercard 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 Mastercard with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Together Fraud Investigations

Stop guessing. Build a ReAct agent that methodically investigates suspicious transactions. Your agent starts with `bin_lookup` to identify the card's origin and type. From there, it can use the transaction details to call `get_merchant` and check if the business location makes sense for the cardholder. The agent decides the next step based on the data it gets back. If multiple flags are raised, it can assemble a complete payload and use `submit_fraud_report`. This isn't a black box. You define the logic, your agent executes it, and LangSmith shows you every single step.

Automate Merchant Due Diligence

Onboarding new business accounts is a tedious, manual process. Use a LangChain agent to do the legwork. Give it a potential merchant's details, and it will use the `validate_account` tool to confirm their bank information is sound. The agent can then cross-reference the business address with `search_merchants` to check for existing listings or conflicts. It can even use `merchant_category_codes` to suggest the correct MCC, which is a common point of failure. You get a consistent, auditable process every time.

Your LangChain MCP Server for Payments

This isn't just about single API calls. It's about building systems. Create a chain that finds a user's location, calls `nearby_locations` to find Mastercard partners, and then uses `get_place_details` to pull specific payment capabilities for a targeted offer. Because it's LangChain, you can easily add other data sources. Pull in your own user data, mix it with real-time merchant info from this MCP server, and let your agent make an informed decision. The output of one tool becomes the input for the next. Simple as that.

Setup guide

Set up Mastercard 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 Mastercard 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({
    "mastercard-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 Mastercard 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 Mastercard. 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 Mastercard 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 Mastercard MCP in LangChain

You'd have your agent call `bin_lookup` first. Then, you'd configure the agent's prompt to use the card type information from that output to decide whether to proceed with `validate_account`. The tools themselves are independent, but the agent's logic connects them.

Yes. When you run your chains with LangSmith tracing active, every call to the Mastercard tools appears as a distinct step. You'll see the exact inputs, outputs, and latency for each tool call.

Your agent's prompt should include instructions for handling API errors. For example, if a `get_merchant` call fails, you can tell the agent to try `search_merchants` with the same coordinates as a fallback. It's about making your agent's logic resilient.

Yes, all 12 tools are exposed and ready to be used by your agent. You just pass the tool list from the MCP client to your agent constructor and it knows how to call them.

The server doesn't store your data. When your LangChain agent uses a tool like `validate_account`, the full account number is passed directly to the Mastercard API endpoint and is not logged by Vinkius. It's your responsibility to ensure your agent's logic and any connected vector stores handle this sensitive data properly.

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