How to Use the Clip API MCP in Pydantic AI

Build type-safe payment agents with Pydantic AI. Validate Clip refunds, subscriptions, and terminal 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 Clip API MCP to Pydantic AI

Create your Vinkius account to connect Clip API 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 Clip API with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Clip API Subscriptions via Pydantic AI

Recurring billing requires strict data validation because mistakes cost money. Connecting this MCP Server to Pydantic AI ensures every `create_subscription_plan` request matches your exact schema before it hits the gateway. If the agent tries to set a negative billing cycle, the framework throws a loud validation error immediately. Voiding active checkout sessions needs the same level of precision. Your agent triggers `cancel_payment_link` when a customer changes their mind about an order. Pydantic AI guarantees the transaction ID format is correct before executing the cancellation.

Manage POS Catalogs Safely

Pushing bad data to a physical cash register ruins the checkout experience. Your agent calls `add_product_to_catalog` to create new SKUs in your Clip account. The framework verifies price integers and string lengths so you never end up with corrupted inventory records. Pulling your current stock list works exactly the same way. Running `list_products_catalog` returns your entire inventory. If the API returns a malformed JSON payload, Pydantic AI catches it at runtime instead of silently passing garbage data to your LLM.

Verify Payments and Issue Refunds

Knowing exactly when a card clears is critical for shipping physical goods. Your system runs `get_transaction_status` to poll the payment state. You get perfectly typed responses back, whether you use OpenAI, Anthropic, or a local model. Returning money requires absolute certainty. Passing `refund_transaction` to your agent lets it process full or partial returns based on customer service chats. You define the exact refund parameters in your Pydantic models, and the framework enforces them strictly.

Setup guide

Set up Clip API 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": {
        "clip-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install the slim package with MCP support. Create an MCPToolset pointing to your Vinkius HTTP endpoint. Pass that toolset array to your Agent instance to register the payment operations.

Every single response runs through your defined schemas. If the gateway returns a status string you didn't account for, the agent fails loudly instead of hallucinating a successful payment.

That older class is deprecated. You should use the unified MCPToolset approach for all remote MCP connections now. It handles Streamable HTTP and SSE transports natively.

The framework is completely model-agnostic. You can validate payment links and refunds using Gemini, Claude, or even a local Llama instance.

Ephemeral sandboxes handle every single request. Your refund amounts and subscription details pass through a V8 isolate that shuts down immediately after the API responds. Vinkius never logs your financial payloads.

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