How to Use the Hyperswitch MCP in OpenAI Agents SDK

Q: How do I connect Hyperswitch to my openai-agents-sdk pipeline?

Install openai-agents via pip and configure the MCP streamable HTTP transport pointing to your Vinkius endpoint. Pass this server instance directly into your Agent constructor using the mcpservers parameter. Your agent will instantly discover all ten payment and dispute tools.

Q: Does the openai-agents-sdk support caching for Hyperswitch tools?

Yes, you should set cacheToolsList=True in your server configuration params. This prevents the SDK from querying the Hyperswitch API schema on every single turn, reducing latency during active checkout sessions.

Q: How does the agent handle payment list pagination?

The listpayments tool returns standard paginated payloads from the API. Parsing the pagination tokens, the agent automatically requests the next page if your prompt asks for a broader date range.

Let your OpenAI Agents SDK run your multi-processor checkouts and resolve disputes autonomously with native Hyperswitch MCP tools.

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 OpenAI Agents SDK

Create your Vinkius account to connect Hyperswitch to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated payment recovery with OpenAI Agents SDK

Your OpenAI Agents SDK can trigger automatic payment checks directly when a user complains about a failed checkout. By calling `get_payment` or pulling history with `list_payments`, the agent pinpoints exactly where the transaction stalled in your multi-processor routing setup without human intervention. Once the agent identifies the failure point, it uses its built-in guardrails to verify if a retry is safe. It then communicates the exact status back to the customer, ensuring no double-charges occur while saving your support team from digging through raw processor logs.

Self-healing dispute management via MCP Server

Chargebacks eat your margins if you ignore them. This MCP Server lets your OpenAI agent actively monitor incoming chargebacks by executing `list_disputes` to gather active claims. The agent uses specialized handoffs to pass the raw dispute data to a verification agent. This agent calls `get_dispute` to pull the precise evidence timeline, matching it against internal database records to prepare your defense package automatically.

Safe customer refund routing

Issuing refunds is risky business for an autonomous agent. By routing `get_refund` and `list_refunds` through the OpenAI SDK tracing dashboard, you can audit every single refund request before it hits the network. The agent verifies the original customer profile using `get_customer` before initiating any refund. You get absolute visibility into how the agent decided to return the money, keeping your financial pipeline clean and secure.

Setup guide

Set up Hyperswitch MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Hyperswitch tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Hyperswitch tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Hyperswitch tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Hyperswitch Agent",
            instructions="You have access to Hyperswitch tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip and configure the MCP streamable HTTP transport pointing to your Vinkius endpoint. Pass this server instance directly into your Agent constructor using the `mcp_servers` parameter. Your agent will instantly discover all ten payment and dispute tools.

Yes, you should set `cacheToolsList=True` in your server configuration params. This prevents the SDK from querying the Hyperswitch API schema on every single turn, reducing latency during active checkout sessions.

You can control access by setting explicit guardrails inside your OpenAI agent definition. This prevents the agent from calling high-risk tools like `get_payout` while still allowing it to query `list_payments` for customer support tasks.

The `list_payments` tool returns standard paginated payloads from the API. Parsing the pagination tokens, the agent automatically requests the next page if your prompt asks for a broader date range.

Your customer payment details and dispute records stay inside the secure Vinkius sandbox. Your OpenAI agent only receives tokenized references and transaction metadata when calling `get_customer` or `get_payment`, keeping raw cardholder data completely out of the LLM context.

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