Integrate Klarna with Claude, Cursor, Chatbots & AI Agents MCP Server

Q: What is the difference between authorizing and capturing an order?

Authorizing only reserves the funds. You must use the captureklarnaorder tool (typically when shipping) to actually move the money from the customer to your account.

Manage payment sessions, orders, and fulfillment via the Klarna REST API.

GDPR Free for Subscribers

Compatible with every major AI agent and IDE

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

+ other MCP clients

cancel

Cancel authorized order on Klarna

Cancel an authorized but uncaptured order

capture

Capture klarna order on Klarna

Capture a formal order to trigger payment

create

Create klarna order on Klarna

Requires an authorization token. Place a formal order using an authorization token

create

Create payment session on Klarna

Requires order amount, currency, and order lines (items). Create a new Klarna payment session

get

Get order details on Klarna

Get details for a specific Klarna order

get

Get payment session on Klarna

Get details for an existing payment session

refund

Refund klarna order on Klarna

Refund a captured order

update

Update order shipping on Klarna

Update shipping information for an order

Security & Code Integrity Audit

Every tool in the Klarna MCP Server is continuously audited by the Vinkius Security Engine. We guarantee zero-trust payload isolation, strict data boundaries, and deterministic execution for enterprise-grade AI agents.

A+Score: 100

How Vinkius protects your data

Can I audit what my AI agents are doing with this integration?

Yes, Vinkius provides an immutable, HMAC-chained audit log. Every tool execution, payload, and response is tracked in real-time on your dashboard, giving you complete visibility into your agent's actions.

How does the AI access my passwords and credentials?

It simply doesn't. On Vinkius, your passwords, API keys, and login details are kept in a secure vault. The AI (like ChatGPT or Claude) merely "asks" Vinkius to perform the task. Vinkius opens the door, does the work, and hands the result back to the AI. Your credentials are never seen, read, or learned by the artificial intelligence.

What is the difference between authorizing and capturing an order?

Authorizing only reserves the funds. You must use the capture_klarna_order tool (typically when shipping) to actually move the money from the customer to your account.

What if the AI ends up reading customer data or confidential information?

We have a built-in digital "bodyguard" called DLP (Data Loss Prevention). If a tool fetches data and the response contains social security numbers, credit cards, or personal customer info, Vinkius magically blocks and erases that information before it is delivered to the AI. The AI works only with what is strictly necessary, and your sensitive data never leaks.

Klarna Capabilities for AI Assistants

Add the Klarna tool to your AI Agents. The toolkit allows Claude and ChatGPT to securely fetch and update targeted data.

The Future of checkout

The Klarna integration allows Cursor and ChatGPT to securely fetch checkout data. It handles the API requests required for money moves operations.

Intelligent buy now pay later Management

Integrate Klarna to access native buy now pay later capabilities. This allows LLMs to perform secure, deterministic execution of money moves tasks without hard-coded API scripts.

Klarna. Runs on everything.

From IDE to framework. Every connection governed by Vinkius.

Claude DesktopIDE

Anthropic's native desktop app for Claude with built-in MCP support.

CursorIDE

AI-first code editor with integrated LLM-powered coding assistance.

VS Code CopilotIDE

GitHub Copilot in VS Code with Agent mode and MCP support.

WindsurfIDE

Purpose-built IDE for agentic AI coding workflows.

ClineIDE

Autonomous AI coding agent that runs inside VS Code.

Claude CodeCLI

Anthropic's agentic CLI for terminal-first development.

OpenAI Agents SDKSDK

Python SDK for building production-grade OpenAI agent workflows.

Google ADKSDK

Google's framework for building production AI agents.

Pydantic AISDK

Type-safe agent development for Python with first-class MCP support.

Vercel AI SDKSDK

TypeScript toolkit for building AI-powered web applications.

Mastra AISDK

TypeScript-native agent framework for modern web stacks.

CrewAIFramework

Python framework for orchestrating collaborative AI agent crews.

LangChainFramework

Leading Python framework for composable LLM applications.

LlamaIndexFramework

Data-aware AI agent framework for structured and unstructured sources.

AutoGenFramework

Microsoft's framework for multi-agent collaborative conversations.

Explore More MCP Servers

View all →

OpenDataSUS

8 tools

Access Brazilian public health data (SUS) directly from your AI. Query datasets, search resources, and analyze health statistics from the official portal.