How to Use the Durianpay MCP in LangChain

Q: Can a LangChain agent run a Durianpay audit automatically?

Yes, you can pass quickrevenuehealthaudit to a LangChain ReAct agent. The agent executes the tool, parses the high-level summary, and formats the transaction success rates for your team.

Q: How is my checkout order and customer profile data secured?

All transaction logs and customer records fetched via listregisteredcustomers run in isolated V8 sandboxes. Vinkius processes these requests on ephemeral hosts, meaning your financial data is never stored on our servers after the tool execution ends.

Run multi-step payment reconciliation chains in LangChain using the Durianpay MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Durianpay MCP to LangChain

Create your Vinkius account to connect Durianpay 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 Durianpay with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Durianpay data directly into your LangChain agents

The `list_payment_orders` tool exposes checkout order data directly to your LangChain ReAct agents via our secure MCP setup. This means your agent can fetch a list of checkout orders and immediately feed those IDs into `get_payment_order_details` within a single execution chain. You do not need to write messy glue code to pass variables between API steps. LangChain handles the state transitions, letting your agent inspect payment statuses and resolve customer inquiries in a single run.

Debug transaction pipelines with LangSmith tracing

The `quick_revenue_health_audit` tool logs and traces every execution step when run by your LangChain agent. LangSmith tracks the latency, token usage, and payload details of `list_latest_transactions` so you see exactly what data your chain receives. This visibility keeps your production runs predictable. If a call to `list_failed_transactions` returns an unexpected error, you pinpoint the exact step in the execution graph without digging through raw server logs.

Combine payment tools with external databases

The `list_registered_customers` tool combines customer profile data with your internal databases inside a LangChain multi-server MCP client. The agent pulls the customer UUID from your database, then queries Durianpay via `get_durianpay_account_metadata` to verify account limits. This setup creates a unified context for complex support tasks. Your agent acts as an autonomous support engineer, resolving billing discrepancies by querying multiple APIs in a logical sequence.

Setup guide

Set up Durianpay 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 Durianpay 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({
    "durianpay-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 Durianpay 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 Durianpay. 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 Durianpay 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 Durianpay MCP in LangChain

You configure backoff behavior directly in your LangChain runnable. When `get_payment_details` hits a rate limit, the chain pauses and retries based on your specified delay strategy before passing the output to the next step.

Yes, you can pass `quick_revenue_health_audit` to a LangChain ReAct agent. The agent executes the tool, parses the high-level summary, and formats the transaction success rates for your team.

Vinkius handles the underlying API credential storage for the MCP Server. Your LangChain client connects using a single endpoint token via the MultiServerMCPClient, removing the need to manage raw API keys in your application code.

Yes, you control tool access during agent initialization. Simply filter the tool list returned by the adapter to only expose specific tools like `list_latest_transactions` while hiding account metadata tools.

All transaction logs and customer records fetched via `list_registered_customers` run in isolated V8 sandboxes. Vinkius processes these requests on ephemeral hosts, meaning your financial data is never stored on our servers after the tool execution ends.

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