How to Use the Cora Bank MCP in Pydantic AI

Build type-safe financial workflows with Pydantic AI to validate Cora Bank transactions and boletos at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cora Bank MCP to Pydantic AI

Create your Vinkius account to connect Cora Bank 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 Cora Bank with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Pix payloads at runtime with Pydantic AI

The `cora_send_pix` tool requires precise parameters before moving any money out of your account. Pydantic AI enforces strict schema validation on the agent's output, ensuring the recipient's tax ID and key are perfectly formatted before the bank API is called. If the model generates an invalid payload, the framework triggers a validation error immediately. This prevents malformed requests from ever reaching the Cora Bank API, saving you from failed transaction fees.

Parse bank statements using type-safe MCP Server schemas

The `cora_get_statement` tool returns structured Brazilian financial data that maps directly to your local Pydantic models. Your agent parses this incoming stream, ensuring every transaction amount, date, and description matches your internal database types. By using `cora_get_balance` alongside your statement parser, you can verify your liquid funds without worrying about silent data corruption. The system fails loudly if the bank returns unexpected fields.

Manage boleto lifecycles with strict model validation

The `cora_create_invoice` tool generates official bank slips and Pix QR codes with guaranteed type safety. The Pydantic AI agent constructs the billing object, validates it against your schemas, and submits the creation request. To keep your billing database accurate, the agent queries `cora_get_invoice` and `cora_list_invoices` to track outstanding debts. If a cancellation is needed, `cora_cancel_invoice` executes with the same rigid schema constraints.

Setup guide

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

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

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

You use the MCPToolset class pointing to your Vinkius HTTP endpoint. Pass this toolset into your Agent instance to give your type-safe workflows direct access to the bank tools.

The framework will raise a validation error instantly instead of passing corrupt data to your agent. This guarantees that tools like `cora_list_payments` only process valid, structured transaction records.

Yes, you can connect over MCP streamable HTTP or SSE using the MCP toolset. This keeps your banking integration responsive while running complex validation checks on your invoices.

Absolutely, the framework is model-agnostic. You can pair local models or alternative APIs with this MCP Server to run private financial analysis without sharing data.

Your billing payloads and bank credentials never sit on Vinkius disks. All traffic passes through secure, isolated V8 instances, keeping your financial data completely private during runtime validation.

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