How to Use the Klarna MCP in OpenAI Agents SDK

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

Install openai-agents via pip. Instantiate MCPServerStreamableHttp with your endpoint, then pass it to the Agent constructor inside the mcpservers list. Set cacheToolsList=True to speed up tool discovery.

Q: Does the Klarna MCP Server track order items?

createpaymentsession requires an exact list of order lines, including prices and quantities. The server passes this payload directly to the API to construct the checkout interface.

Build production-grade checkout flows with the OpenAI Agents SDK and this 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 Klarna MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Initialize Payment Sessions with OpenAI Agents SDK

`create_payment_session` sets up the initial checkout state by passing the order amount, currency, and line items directly from your agent. Your AI client handles the math, calculates totals, and generates the session token required for the frontend. Once the user approves the purchase, `create_klarna_order` consumes that authorization token to lock in the transaction. You track the entire handoff inside the OpenAI dashboard, ensuring specialized agents only execute payment steps when strict guardrails pass.

Trigger Fulfillment Workflows

`capture_klarna_order` converts an authorized hold into an actual charge against the customer's account. This happens immediately after your logistics system confirms the box left the warehouse. You keep the customer loop closed using `update_order_shipping` to attach tracking numbers to the transaction. If a shipment gets delayed, the agent checks the status via `get_order_details` and decides whether to hold the capture.

Handle Exceptions and Reversals

`refund_klarna_order` pushes money back to the buyer for captured orders that encounter post-sale issues. The agent calculates the exact return value and executes the request without human intervention using this MCP Server. For orders that never shipped, `cancel_authorized_order` drops the pending hold entirely. You use `get_payment_session` to verify the exact state before pulling the plug, preventing accidental double-refunds in your production environment.

Setup guide

Set up Klarna 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 Klarna tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` via pip. Instantiate `MCPServerStreamableHttp` with your endpoint, then pass it to the Agent constructor inside the `mcp_servers` list. Set `cacheToolsList=True` to speed up tool discovery.

Yes. You write a specialized support agent that evaluates return policies and calls `refund_klarna_order`. Built-in guardrails require a human-in-the-loop approval step before the money actually moves.

`create_payment_session` requires an exact list of order lines, including prices and quantities. The server passes this payload directly to the API to construct the checkout interface.

You likely forgot to use an async context manager when initializing the server connection. The SDK requires an active async session to auto-discover the eight exposed endpoints.

The server processes authorization tokens and line-item totals, never raw credit card strings. The V8 Isolate Sandbox destroys the execution environment the millisecond the request finishes, leaving zero trace of the transaction data.

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