How to Use the Checkout.com MCP in LangChain

Build complex payment pipelines using LangChain agents and this MCP Server. Run transactions, capture funds, and trace every step.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Checkout.com MCP to LangChain

Create your Vinkius account to connect Checkout.com 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 Checkout.com with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Multi-Step Payment Chains

The `request_payment` tool initiates transactions directly from your LangChain agent. You define the exact sequence of events. When an order drops into your system, the agent hits the Checkout.com API, grabs the response, and immediately feeds that CRM record into the next node. Passing context matters here. If a charge needs authorization before clearing, your ReAct agent holds the state and triggers `capture_payment` automatically based on your custom logic. You see exactly which tool fired, the latency, and the token cost right inside your LangSmith dashboard.

Manage Vaulted Instruments via MCP Server

Your agent provisions customer cards using the `create_instrument` tool. This creates a hard binding to a JSON payload without exposing raw card numbers in your prompt logs. LangChain handles the schema validation before the request ever hits the Vinkius endpoint. Managing churn becomes a simple chain. You can instruct the agent to run `get_instrument` to check active Vault logic, then fire `delete_instrument` to wipe expired cards. Every operation links together, turning manual billing checks into an automated background process.

Automate Refunds and Voids

The `void_payment` tool drops authorization limits before a capture closes. This cuts out heavy gateway fees when orders get cancelled fast. Your agent decides between a void and a full refund based on the transaction lifecycle state. For settled charges, the chain routes to `refund_payment` instead. Cash moves back to the originating Visa or Mastercard network. Because you built this in LangChain, the MCP Server can simultaneously update your internal database or notify the customer via another tool in the same run.

Setup guide

Set up Checkout.com 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 Checkout.com 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({
    "checkoutcom-1-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 Checkout.com 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 Checkout.com. 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 Checkout.com 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 Checkout.com MCP in LangChain

Install the langchain-mcp-adapters package and define a MultiServerMCPClient. Pass your Vinkius endpoint URL. Call client.get_tools() to inject the payment tools into your agent.

Yes. Your agent can read a cancellation request and trigger the refund_payment tool. It automatically routes the exact amount back to the customer's card.

LangSmith traces the exact error output from the MCP server. Your ReAct agent reads the failure reason and can retry with a different tool or alert a human operator.

You can combine the Checkout.com MCP Server with your database or CRM tools in the same LangChain setup. The agent pulls customer data from one server and charges them via another.

Vinkius isolates execution in a V8 sandbox. Your agent touches Vault tokens and transaction IDs, never raw credit card numbers. Ephemeral sessions mean the server forgets the data the second your chain finishes running.

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