How to Use the Checkout.com MCP in Pydantic AI

Q: How do I install the Checkout.com MCP Server for Pydantic AI?

Install the slim package with pip install "pydantic-ai-slimmcp". Use the unified MCPToolset class with your HTTP endpoint and pass it to your Agent constructor.

Q: Does Pydantic AI validate Checkout.com API responses?

Yes. Every time the agent runs a tool like refundcheckoutpayment, the framework validates the output against your defined Pydantic models at runtime.

Type-safe Checkout.com integration for Pydantic AI. Validate every payment action at runtime and prevent silent API failures.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Checkout.com MCP to Pydantic AI

Create your Vinkius account to connect Checkout.com 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 Checkout.com with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict validation for Pydantic AI

Financial operations demand exact schemas in your MCP environment. When your agent calls `capture_checkout_payment`, Pydantic AI validates the required fields against strict models before the request ever hits the network. If the API returns an unexpected string instead of an integer for the amount, the framework throws a validation error immediately. Your agent fails loudly instead of passing hallucinated transaction data downstream.

Type-safe payment retrieval

Connect your MCP Server and stop guessing what the JSON payload looks like. You define the expected structure for `get_payment_details`, and the agent forces the response into that exact shape. This means your payment logic stays predictable. The agent fetches recent charges with `list_checkout_payments`, and your Python code handles the parsed objects without writing custom dictionary lookups or error handling blocks.

Audit accounts without silent errors

Debugging billing integrations usually involves digging through raw logs. Here, your MCP agent hits `get_checkout_account_info` and maps the merchant details directly into your application state. If you need to verify system events, the agent checks `list_checkout_webhooks`. Pydantic AI guarantees the URLs and active statuses match your expected types, so your automated audits never break silently.

Setup guide

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

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

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

Install the slim package with `pip install "pydantic-ai-slim[mcp]"`. Use the unified `MCPToolset` class with your HTTP endpoint and pass it to your Agent constructor.

Yes. Every time the agent runs a tool like `refund_checkout_payment`, the framework validates the output against your defined Pydantic models at runtime.

You can. The framework is model-agnostic. You connect an open-source model, and it interacts with the payment API exactly like a commercial provider would.

Raw calls require manual error parsing. The agent handles the conversational logic to figure out which transaction to void, while the framework ensures the data types match perfectly.

Authentication happens at the Vinkius layer, meaning your local environment only needs a single endpoint token. The agent processes payment IDs and authorization codes, but the underlying credentials never touch your Pydantic AI 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