How to Use the Durianpay MCP in OpenAI Agents SDK

Q: How do I connect Durianpay to the OpenAI Agents SDK?

Install the package with pip install openai-agents first. Initialize MCPServerStreamableHttp pointing to the Vinkius endpoint, then pass it to your Agent constructor.

Q: Does the OpenAI Agents SDK cache Durianpay tool definitions?

It does if you configure it to. Setting cacheToolsList=True ensures the OpenAI Agents SDK doesn't waste network cycles re-fetching the tool schemas on every single turn.

Let your OpenAI Agents SDK production agents audit transaction logs and track checkout orders directly through the Durianpay API.

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 OpenAI Agents SDK

Create your Vinkius account to connect Durianpay 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 Durianpay with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track checkout states with OpenAI Agents SDK

Stop manually checking your payment dashboards. Let your agent pull live data using `get_payment_order_details` and `list_payment_orders` to resolve customer checkout issues on the fly. The agent uses these tools to match order IDs with actual payment attempts. By querying the Durianpay API directly via our MCP Server inside your execution loop, your system flags stuck checkouts before customers abandon their carts.

Run instant revenue audits via MCP Server tools

Your agent can inspect financial health without writing custom database queries. Trigger `quick_revenue_health_audit` to get a snapshot of payment success rates and volume metrics. Combine this audit with `list_latest_transactions` to track incoming cash flow. It gives your financial operations team a clear view of transaction patterns without manual CSV exports.

Diagnose transaction failures instantly

Payment declines happen, but finding out why shouldn't take ten minutes of digging. Use `list_failed_transactions` and `get_payment_details` to pinpoint exactly where a transaction dropped. Your agent inspects the failure codes and cross-references them with `list_registered_customers` to see if a specific user has repeated issues. This fast feedback loop saves your support desk hours of manual research.

Setup guide

Set up Durianpay 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 Durianpay tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Durianpay 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="Durianpay Agent",
            instructions="You have access to Durianpay 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 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 OpenAI Agents SDK

Install the package with `pip install openai-agents` first. Initialize `MCPServerStreamableHttp` pointing to the Vinkius endpoint, then pass it to your Agent constructor.

Yes, because the SDK handles tool execution loops natively. If a tool like `list_durianpay_payments` hits a rate limit, the SDK's built-in retry logic manages the backoff automatically.

It does if you configure it to. Setting `cacheToolsList=True` ensures the OpenAI Agents SDK doesn't waste network cycles re-fetching the tool schemas on every single turn.

You control access by defining specific system prompts or limiting the tools passed to the agent. If you only want to allow read-only tasks, expose `get_payment_details` while withholding metadata tools.

Absolutely. Your API keys and transactional records never persist in the Vinkius sandbox environment. Every request to endpoints like `get_durianpay_account_metadata` runs in an ephemeral, isolated container that instantly wipes its memory after execution.

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