How to Use the IBAN.com MCP in Pydantic AI

Q: How do I initialize the IBAN.com MCP Server in Pydantic AI?

Install pydantic-ai-slimmcp and use the unified MCPToolset constructor pointing to your server URL. Pass this toolset into the toolsets argument of your Agent. Avoid using the deprecated MCPServerHTTP class for this setup.

Q: Does the IBAN.com MCP Server support Pydantic AI runtime validation?

Yes, every response from tools like getbankdetails is parsed and validated against concrete schemas. This ensures your agent only works with clean, structured bank metadata. Any schema mismatch triggers a loud validation error immediately.

Q: Can I monitor my API credits using IBAN.com and Pydantic AI?

Yes, your agent can call getapibalance to retrieve your remaining credit count as a typed integer. This allows you to build programmatic guardrails that halt execution if your balance is too low. It prevents runtime failures during high-volume payment runs.

Q: How does this MCP Server validate credit cards?

The validatecardluhn tool uses the Luhn algorithm to check card number formats. The output is returned as a validated boolean, allowing your agent to reject bad card numbers instantly. This keeps your payment forms clean and reduces gateway fees.

Run type-safe bank validation using Pydantic AI to enforce strict schemas on IBAN and SWIFT checks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IBAN.com MCP to Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict type validation for Pydantic AI

The `validate_iban` tool returns structured bank metadata that is validated against strict Python type schemas at runtime. If the API returns unexpected field formats, Pydantic AI fails immediately, preventing corrupted data from entering your database. You configure this setup by importing the MCP library and passing your server URL. The agent maps the JSON response directly to your defined data models, ensuring 100% type safety for your financial workflows.

Verify SWIFT codes with zero silent errors

The `validate_swift_bic` tool checks the validity of bank codes and returns structured routing details. Because Pydantic AI validates every response, your agent cannot hallucinate or misinterpret the SWIFT status. This MCP Server integration gives you absolute certainty that the routing code is valid before you execute a transaction. It eliminates the silent failures common in unstructured agent platforms.

Calculate IBANs with runtime schema enforcement

The `calculate_iban` tool converts local account numbers into valid international formats. Your agent runs this calculation and immediately parses the output into a verified Pydantic model. If the calculation fails due to an invalid routing code, the tool returns a structured error. Your agent catches this validation error programmatically, allowing you to handle payment exceptions before they reach your billing engine.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` and use the unified `MCPToolset` constructor pointing to your server URL. Pass this toolset into the `toolsets` argument of your Agent. Avoid using the deprecated `MCPServerHTTP` class for this setup.

Yes, every response from tools like `get_bank_details` is parsed and validated against concrete schemas. This ensures your agent only works with clean, structured bank metadata. Any schema mismatch triggers a loud validation error immediately.

Yes, your agent can call `get_api_balance` to retrieve your remaining credit count as a typed integer. This allows you to build programmatic guardrails that halt execution if your balance is too low. It prevents runtime failures during high-volume payment runs.

The `validate_card_luhn` tool uses the Luhn algorithm to check card number formats. The output is returned as a validated boolean, allowing your agent to reject bad card numbers instantly. This keeps your payment forms clean and reduces gateway fees.

This MCP Server runs in a secure, ephemeral V8 isolate that processes credit card numbers and bank codes without saving them to disk. The `validate_card_luhn` and `validate_iban` tools discard all input data immediately after the check completes. Your credentials and payloads are completely isolated from other workflows.

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