How to Use the Hyperswitch MCP in LangChain

Q: Can LangChain handle complex routing decisions across multiple Hyperswitch tools?

Yes. Your agent can evaluate transaction history using listpayments and customer profiles from getcustomer to decide whether to trigger automated refunds via getrefund.

Q: What is the best way to handle failed Hyperswitch refunds in LangChain?

Set up a fallback chain that listens for failures from getrefund. If a refund fails, the agent can run listpayments to verify the original capture state before logging the error.

Run multi-processor payment flows through LangChain chains using Hyperswitch tool outputs as inputs for your next agent step.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hyperswitch MCP to LangChain

Create your Vinkius account to connect Hyperswitch 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 Hyperswitch with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain payment lookups with LangChain logic

LangChain links your payment operations into logical sequences. Your agent runs `list_payments` to find stuck transactions, then passes those exact IDs to `get_payment` to figure out why the processor choked. You don't write glue code. The output of one Hyperswitch tool feeds directly into the next step of your chain. This setup shines when handling failed transactions. If a payment fails, your agent checks the customer history with `get_customer` and instantly triggers a retry or flags the account. You get clean, step-by-step execution without manual intervention.

Trace Hyperswitch MCP Server calls in LangSmith

Stop guessing why a refund failed. When your LangChain agent calls `get_refund` or `list_refunds` via this MCP Server, LangSmith captures every single detail. You see the exact payload sent to Hyperswitch, the latency of the network hop, and the raw JSON response. Debugging payments is usually a nightmare of scattered logs. This integration puts your payment API calls right alongside your prompt templates and LLM token usage. If a dispute lookup via `get_dispute` takes too long, you'll spot the bottleneck in seconds.

Automate dispute mitigation pipelines

Build autonomous agents that monitor your incoming chargebacks. The agent runs `list_disputes` to gather recent challenges, then uses `get_dispute` to pull the specific evidence requirements. It's a hands-off way to keep your processor accounts in good standing. Because LangChain connects to hundreds of external vector databases, your agent can grab the original customer contract, draft a response, and prepare the dispute defense. You turn manual finance chores into a self-running loop.

Setup guide

Set up Hyperswitch 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 Hyperswitch 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({
    "hyperswitch-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 Hyperswitch 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 Hyperswitch. 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 Hyperswitch 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 Hyperswitch MCP in LangChain

Install the langchain-mcp-adapters package and initialize the MultiServerMCPClient with your Vinkius server URL. Call get_tools on the client to register the Hyperswitch tools, then pass them directly to your agent's tool list.

Yes. Your agent can evaluate transaction history using list_payments and customer profiles from get_customer to decide whether to trigger automated refunds via get_refund.

Set up a fallback chain that listens for failures from get_refund. If a refund fails, the agent can run list_payments to verify the original capture state before logging the error.

LangChain remains stateless by default. If you need to track pagination across multiple list_payouts requests, use client.session() to maintain context within your running chain.

Your raw transaction logs, customer IDs, and refund details pass through our secure MCP sandbox. No payment data is stored on Vinkius servers, keeping your PCI-DSS scope clean.

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