How to Use the Klarna MCP in Google ADK

Q: How do I configure Klarna for the Google ADK?

Install the google-adk package and set up McpToolset with your HTTP endpoint. Pass this toolset directly to the LlmAgent initialization. You can filter the eight available tools using the toolnames parameter.

Q: Can Google ADK agents read past Klarna transactions?

They read current states via getorderdetails. For historical analysis, you dump the output of these API calls into BigQuery, letting Gemini cross-reference past purchases with current support tickets.

Q: Does the Klarna MCP Server handle shipping updates?

You call updateordershipping to push merchant references and tracking codes. The agent extracts tracking numbers from logistics emails and feeds them directly into the API.

Q: How do I prevent Google ADK from capturing Klarna orders too early?

You write strict system prompts that block captureklarnaorder until a specific database row changes. The framework enforces these constraints before allowing the HTTP transport to fire.

Connect the Klarna MCP Server to the Google ADK and process checkout data directly alongside your BigQuery pipelines.

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 Google ADK

Create your Vinkius account to connect Klarna to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate Checkout Sessions

`create_payment_session` builds the foundation of the checkout process by accepting cart items, currency, and total amounts. Your Gemini agent reads inventory levels from BigQuery and dynamically constructs the payload. After the buyer authenticates on the frontend, `create_klarna_order` finalizes the purchase using the returned authorization token. The massive context window of Vertex AI means your agent remembers the entire user journey leading up to the transaction.

Automate Capture with Google ADK

`capture_klarna_order` tells the API to pull funds from the buyer's account via this MCP Server. You trigger this action the moment your warehouse management system updates the order status in Google Cloud. Your agent then calls `update_order_shipping` to append carrier details to the record. Logistics teams query `get_order_details` to verify the tracking numbers match the physical packages sitting on the dock.

Execute Financial Reversals

`refund_klarna_order` reverses settled transactions when customers return merchandise. The agent calculates the exact refund fraction based on return policies stored in your cloud database. If an order gets flagged for fraud before shipping, `cancel_authorized_order` removes the pending authorization. You run `get_payment_session` first to confirm the exact session state, preventing errors during automated cancellation sweeps.

Setup guide

Set up Klarna MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Klarna tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Klarna_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Klarna tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the `google-adk` package and set up `McpToolset` with your HTTP endpoint. Pass this toolset directly to the `LlmAgent` initialization. You can filter the eight available tools using the `tool_names` parameter.

They read current states via `get_order_details`. For historical analysis, you dump the output of these API calls into BigQuery, letting Gemini cross-reference past purchases with current support tickets.

You call `update_order_shipping` to push merchant references and tracking codes. The agent extracts tracking numbers from logistics emails and feeds them directly into the API.

You write strict system prompts that block `capture_klarna_order` until a specific database row changes. The framework enforces these constraints before allowing the HTTP transport to fire.

The integration moves order lines, currency codes, and shipping references across an ephemeral connection. Vinkius manages the authentication layer, ensuring zero-trust execution where no state persists after the connection drops.

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