Are actions simulated or operating live on real Ledgers?

If you inject your core Project Access Token with full production permissions and leave the `env` string off `sandbox`, yes! It executes heavy Core Banking GraphQL mutations that immediately provision legally compliant EU ledgers behind the scenes.

Can the AI Agent manage physical or virtual credit cards?

Yes. Via `swan_add_virtual_card` and `swan_cancel_card` the LLM has complete programmatic control over debit and spend cards mapped to underlying accounts.

Does the system support sandbox incoming money simulation?

Yes! We expose the `swan_simulate_incoming_transfer` specifically so you can test your programmatic workflows in SandBox by pushing fake money into target ledgers.

Swan MCP Server for Pydantic AI 9 tools — connect in under 2 minutes

Name: Swan
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 9 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Swan through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Swan "
            "(9 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Swan?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Swan MCP Server

The Swan MCP Server embeds a complete European Banking-as-a-Service architecture into Vinkius LLMs.

Pydantic AI validates every Swan tool response against typed schemas, catching data inconsistencies at build time. Connect 9 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Automated Root Provisioning — Instantly spin up local branch operations allocating FRA or ESP IBAN formats through swan_create_account.
Card Administration — Ask the agent to generate custom virtual Mastercards assigned exclusively to distinct contractors utilizing swan_add_virtual_card.
Direct SEPA Execution — Move exact funds safely parsing external creditor data natively through swan_create_sepa_transfer directly across European networks.

The Swan MCP Server exposes 9 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Swan to Pydantic AI via MCP

Follow these steps to integrate the Swan MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 9 tools from Swan with type-safe schemas

Why Use Pydantic AI with the Swan MCP Server

Pydantic AI provides unique advantages when paired with Swan through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Swan integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Swan connection logic from agent behavior for testable, maintainable code

Swan + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Swan MCP Server delivers measurable value.

Type-safe data pipelines: query Swan with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Swan tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Swan and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Swan responses and write comprehensive agent tests

Swan MCP Tools for Pydantic AI (9)

These 9 tools become available when you connect Swan to Pydantic AI via MCP:

swan_add_virtual_card

Provisions a robust Mastercard Virtual Debit

swan_cancel_card

Permanently cancel a specific corporate card

swan_create_account

Requires an existing AccountHolderId. Dynamically provision a European Account under your ledger

swan_create_sepa_transfer

Initiate a standard European SEPA Credit Transfer

swan_get_accounts

List all operational Swan Bank Accounts/IBANs

swan_get_project_info

Fetch overarching details about your connected Swan Project Node

swan_get_transactions

Retrieve the ledger history for a specific Account

swan_list_cards

List all physical and virtual cards

swan_simulate_incoming_transfer

Sandbox Only - Inject fake money

Example Prompts for Swan in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Swan immediately.

"Retrieve my core project identifier and map the legal entity ID."

"Launch a brand new sub-account in France. Bind it to the root entity targeting EUR processing."

"Sweep the ledger of Account X123 and list the latest 5 transactions."

Troubleshooting Swan MCP Server with Pydantic AI

Common issues when connecting Swan to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Swan + Pydantic AI FAQ

Common questions about integrating Swan MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Swan MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.