How to Use the Blink Payment MCP in Pydantic AI

Q: How does Pydantic AI validate data returned from Blink Payment?

When your agent calls getpayment, the MCP framework intercepts the JSON response and parses it into a Pydantic model. If the gateway returns an unexpected field or a missing value, Pydantic AI raises a validation error immediately.

Run type-safe financial operations using Blink Payment and Pydantic AI to guarantee zero data corruption.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Blink Payment MCP to Pydantic AI

Create your Vinkius account to connect Blink Payment 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 Blink Payment with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Blink Payment tools for Pydantic AI

The `create_payment_intent` and `refund_payment` tools are fully validated at runtime by Pydantic AI's strict type engine. This prevents your agent from passing bad currencies or malformed amounts to the Blink Payment gateway, raising a clear validation error instead of failing silently. Because Pydantic AI is model-agnostic, you can swap your underlying LLM from OpenAI to Anthropic without rewriting your Blink Payment logic. Your Pydantic AI application can rely on the structured, type-safe data schemas returned by the MCP tools.

Strict validation for customer records

The `create_customer` and `get_customer` tools ensure your Pydantic AI client directory remains clean and consistent. When your agent queries `list_customers`, the response is parsed against strict Pydantic models to catch missing Blink Payment fields before they hit your database. If a Blink Payment customer profile has an unexpected format, the Pydantic AI framework rejects the payload instantly. This protects your downstream CRM syncs from breaking due to LLM hallucinations or weird formatting issues.

Validated paylink generation

The `create_paylink` tool allows your Pydantic AI agent to safely generate links while verifying the output structure. Your agent can check the generated link using `get_paylink` and verify the URL structure matches your expectations before displaying it to the user. Setting this up requires passing the Vinkius MCP toolset into your Pydantic AI `Agent` constructor. Every field in `list_paylinks` is guaranteed to conform to your type definitions by Pydantic AI while the system handles the underlying network requests.

Setup guide

Set up Blink Payment 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": {
        "blink-payment-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

When your agent calls `get_payment`, the MCP framework intercepts the JSON response and parses it into a Pydantic model. If the gateway returns an unexpected field or a missing value, Pydantic AI raises a validation error immediately.

You use the MCP toolset class pointing to your Vinkius HTTP endpoint. Pass this toolset directly into the `toolsets` list of your Pydantic AI `Agent` constructor to give your model access to `create_paylink` and other tools.

Yes, Pydantic AI is model-agnostic. You can connect a local model to the agent, and it will still be able to run `list_payments` safely because the framework handles the validation on the Python side.

No, the old HTTP class is deprecated in favor of the unified `MCPToolset` approach. Make sure to update your Pydantic AI dependencies to `pydantic-ai-slim[mcp]` to use the modern toolset import.

All API calls to fetch customer email addresses or payment statuses are routed through Vinkius's secure sandbox. Pydantic AI validates the data locally in your memory space, ensuring sensitive customer information never gets stored on external servers.

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