How to Use the Stark Bank MCP in Pydantic AI

Q: Can Pydantic AI help with Stark Bank payment validation?

Yes, this is its strength. When listing transactions using starklisttransfers or starklistpixcharges, the response is immediately checked against your defined models. You never trust garbage data.

Q: Can I check my current balance using Stark Bank with Pydantic AI?

You call starkgetbalance, and Pydantic validates that the returned value is actually a currency type (e.g., float or decimal). This guarantees the number you use for calculations is correct.

Ensure financial data correctness with Pydantic AI and Stark Bank's structured tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Stark Bank MCP to Pydantic AI

Create your Vinkius account to connect Stark Bank to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Stark Bank with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Create Structured Payments

When creating a payment, you define the exact output schema. Whether it’s generating a Boleto via `stark_create_boleto` or making an immediate Pix charge using `stark_create_pix_charge`, Pydantic validates every field. If the API sends bad data, your agent fails loudly.

Validate Card and Transfer Details

The agent handles corporate card creation via `stark_create_corporate_card` and transfers using `stark_create_transfer`. Pydantic ensures that all required parameters—like account numbers or due dates—are present and correctly formatted before the call is made.

Schema-Validated Reporting

You can get a statement by calling `stark_get_statement`, but Pydantic doesn't stop there. It validates that the resulting data fields match your expected model, preventing silent corruption when analyzing cash flow.

Setup guide

Set up Stark Bank 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": {
        "stark-bank-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Pydantic enforces type safety on every piece of data coming from the MCP Server. It treats the tool calls as guaranteed inputs, meaning your agent's logic always receives clean, predictable structured results.

Yes, this is its strength. When listing transactions using `stark_list_transfers` or `stark_list_pix_charges`, the response is immediately checked against your defined models. You never trust garbage data.

If the bank's API returns unexpected fields, or a required field is missing, your agent doesn't just guess—it throws a clear validation error. You know exactly where the data corruption happened.

This server touches critical financial records like transaction histories and balances. Pydantic ensures that even if the tool output is large, you can precisely model and handle only the specific data types you need.

You call `stark_get_balance`, and Pydantic validates that the returned value is actually a currency type (e.g., float or decimal). This guarantees the number you use for calculations is correct.

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