How to Use the Brankas MCP in Pydantic AI

Q: How do I initialize Brankas in Pydantic AI?

Install the library using pip install "pydantic-ai-slimmcp" and initialize MCPToolset with your Vinkius HTTP URL. Pass this toolset into the toolsets argument of your Agent constructor.

Secure your Brankas open finance integrations with runtime type safety using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Brankas MCP to Pydantic AI

Create your Vinkius account to connect Brankas 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 Brankas with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run type-validated disbursements using Pydantic AI

This implementation uses `inter_bank_transfer` and `intra_bank_transfer` to trigger bank payouts with strict runtime validation. Every transfer parameter, from bank codes to currency formats, is validated against Pydantic schemas before hitting the bank API. If your agent tries to pass an invalid bank code or an incorrect decimal format, the framework raises a validation error immediately. This prevents bad transfer payloads from ever leaving your application.

Extract structured bank data with this MCP Server

This feature uses `get_statement` and `get_balance` to pull raw financial records and parse them into strongly-typed Python objects. Pydantic AI validates every transaction row to ensure dates and amounts match your expected types. If a bank returns an unexpected null value or a malformed string, the validation layer catches it before it pollutes your database. This keeps your financial reporting pipeline completely clean.

Build bulletproof Brankas checkout flows with Pydantic AI

This workflow uses `create_checkout`, `get_transaction`, and `get_identities` to manage user checkout sessions and verify customer identity. The agent validates the customer's identity data against your internal user models in real-time. By using this integration, your agent can safely check payment statuses without risk of silent failures. Any unexpected API response triggers a loud runtime exception that your system can catch and handle gracefully.

Setup guide

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

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

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

Install the library using `pip install "pydantic-ai-slim[mcp]"` and initialize `MCPToolset` with your Vinkius HTTP URL. Pass this toolset into the `toolsets` argument of your `Agent` constructor.

The framework will raise a validation error instantly, preventing your agent from processing corrupted data. This ensures that any changes to the transaction schema are caught at runtime rather than failing silently.

Yes, the framework is model-agnostic, meaning you can run your banking workflows using Claude, GPT-4, or local models while maintaining the same strict runtime validation.

You call the transfer status tool through the agent, which validates the returned status string against your defined status enum. This guarantees your application logic only receives valid transaction states.

Identity data retrieved from local banks is validated locally within your Python runtime. The Vinkius MCP gateway ensures the framework does not store or leak your customers' personal details to external logging platforms.

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