How to Use the Afterpay MCP in Pydantic AI

Build type-safe Afterpay integrations using Pydantic AI to validate payment data at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Afterpay MCP to Pydantic AI

Create your Vinkius account to connect Afterpay 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 Afterpay with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe checkout validation with Pydantic AI

Your agent can safely run `create_checkout` because every response is validated against strict Python types. If the API returns unexpected checkout data, Pydantic AI fails loudly before your system processes the broken payload. This strict validation applies to `get_afterpay_config` as well. The MCP Server ensures that merchant limits are parsed as exact numerical types, preventing silent data corruption in your pricing logic.

Validate Afterpay payment details with zero hallucinations

When fetching transaction records, your agent uses `get_payment_details` to pull settlement information. Pydantic AI guarantees that every returned field matches your schema, eliminating hallucinated transaction IDs or missing dates. If you need to audit multiple accounts, the agent runs `list_payments` to fetch historical logs. The framework parses these payment arrays into type-safe Python lists, making it easy to run calculations without worrying about null values.

Safe refund execution using Pydantic AI models

Processing a refund via `refund_payment` requires exact balance checks to avoid double-crediting. Your agent uses this tool inside a type-safe workflow that validates the remaining balance before sending the refund request. Because this MCP setup is model-agnostic, you can use OpenAI or Anthropic models to trigger the refund. Pydantic AI acts as the runtime guard, ensuring the LLM's output conforms to your exact API schema.

Setup guide

Set up Afterpay 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": {
        "afterpay-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Afterpay 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 Afterpay. 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 Afterpay 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 Afterpay MCP in Pydantic AI

Use the unified toolset class with your server's HTTP endpoint. Pass this toolset directly into your Agent's constructor to expose tools like `create_checkout` and `list_payments`.

The framework will raise a validation error immediately. This prevents your agent from making decisions based on malformed payloads when running `get_payment_details`.

Yes, Pydantic AI is completely model-agnostic. You can connect local models to tools like `get_afterpay_config` while maintaining strict runtime schema validation.

Yes, the framework supports both Streamable HTTP and SSE transports. This allows your agent to communicate securely with the server hosted on Vinkius.

This toolset processes checkout sessions, refund logs, and customer payment details. Since Vinkius hosts the server in an ephemeral sandbox, your credentials and customer data are isolated, and the type-safe validation happens entirely within your local runtime.

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