How to Use the Klarna MCP in Pydantic AI

Q: How do I load Klarna tools into Pydantic AI?

Install pydantic-ai-slimmcp and define your server using MCPToolset. Pass the toolset to your Agent instance. The framework automatically converts the eight endpoints into strictly typed Python functions.

Q: Does this MCP Server support partial refunds?

You specify the exact integer amount when calling refundklarnaorder. The API processes whatever value you send, provided it does not exceed the original captured total.

Bring strict runtime validation to Klarna transactions using Pydantic AI 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 Pydantic AI

Create your Vinkius account to connect Klarna to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Payment Sessions

`create_payment_session` accepts strict inputs for order amount, currency, and line items through this MCP Server. If the LLM hallucinates a currency code or misses a required field, Pydantic AI throws a hard validation error before the API request ever fires. The agent moves forward by executing `create_klarna_order` with a valid authorization token. You rely on these strict schemas to guarantee that malformed financial requests never reach the production endpoint.

Validate Captures with Pydantic AI

`capture_klarna_order` pushes the final charge through the system once fulfillment is complete. Your model-agnostic agent reads the warehouse status and triggers the capture exactly when the rules dictate. You supply tracking data via `update_order_shipping` to keep the merchant record accurate. If the agent needs to verify the current state, it runs `get_order_details` and maps the JSON response directly into a validated Python object.

Process Verified Reversals

`refund_klarna_order` sends money back for completed orders that require adjustment. The framework ensures the refund amount matches the specific schema requirements, failing loudly if the agent tries to refund more than the capture amount. `cancel_authorized_order` voids the transaction if the customer backs out before shipping. You execute `get_payment_session` to check the authorization status, preventing the agent from sending a cancellation payload to an already captured order.

Setup guide

Set up Klarna MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "klarna-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Klarna tools.",
)

result = await agent.run("List recent Klarna transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]` and define your server using `MCPToolset`. Pass the toolset to your Agent instance. The framework automatically converts the eight endpoints into strictly typed Python functions.

Yes. If the language model generates an unsupported currency string for `create_payment_session`, the runtime validation blocks execution immediately. The agent receives the error and retries with the correct format.

You specify the exact integer amount when calling `refund_klarna_order`. The API processes whatever value you send, provided it does not exceed the original captured total.

Financial APIs require exact data structures, and raw LLM outputs are unpredictable. This framework forces every generated payload to pass schema checks, eliminating silent data corruption during checkout flows.

It handles session IDs, authorization tokens, and cart totals without storing them on disk. The V8 sandbox environment spins up for the exact duration of the request and completely annihilates itself once the response returns.

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