How do I encode my Cora `.pem` certificates properly?

Head to Cora Bank's portal and setup an API App yielding you exactly the Client Credentials and a certificate pairing (Public CERT `.pem`/`.crt` and Private `.key`). Go to a UNIX shell / MacOS Terminal: `base64 -i my_key.key` to get the key text, and `base64 -i my_cert.pem` to get the cert text. The unformatted, unbroken blocks are the credentials you paste directly to us.

Does Cora produce a separate Pix link from its Boleto command?

In Cora's domain, executing `cora_create_invoice` natively packages everything. A single entity 'Invoice' acts as both your printable boleto format AND a highly specific Dynamic QR Pix, ensuring multiple avenues for your clients.

Will an outgoing Pix from my chat be instant?

Absolutely. Emitting an explicit request down the `cora_send_pix` route connects instantaneously down Cora's active routing engine (Sistema de Pagamentos Instantâneos - SPI/Bacen) draining specific liquidity.

Can I cancel unpaid user invoices rapidly from MCP?

Of course! Call upon the unneeded identifier within your chat interface, prompting the logic `cora_cancel_invoice`, pulling the document from global banking registration.

Cora Bank MCP Server for Pydantic AI 8 tools — connect in under 2 minutes

Name: Cora Bank
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 8 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Cora Bank through 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 Cora Bank "
            "(8 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Cora Bank?"
    )
    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 Cora Bank MCP Server

The Cora Bank MCP Server attaches your corporate entity directly to your AI programming or conversational agent via officially supported backend APIs.

Pydantic AI validates every Cora Bank tool response against typed schemas, catching data inconsistencies at build time. Connect 8 tools through 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

Invoicing Power — Utilize native cora_create_invoice to print a highly detailed digital invoice that simultaneously displays a standard Brazilian Boleto barcode and a Pix QR code for max conversion mapping.
Payment Outs — Fire cora_send_pix securely via text interactions without opening separate mobile applications to clear out daily vendor tabs.
Status Overviews — Keep track of unread metrics through statements queries, canceling generated invoices smoothly.

The Cora Bank MCP Server exposes 8 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 Cora Bank to Pydantic AI via MCP

Follow these steps to integrate the Cora Bank 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 8 tools from Cora Bank with type-safe schemas

Why Use Pydantic AI with the Cora Bank MCP Server

Pydantic AI provides unique advantages when paired with Cora Bank 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 Cora Bank integration code

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

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

Cora Bank + Pydantic AI Use Cases

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

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

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

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

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

Cora Bank MCP Tools for Pydantic AI (8)

These 8 tools become available when you connect Cora Bank to Pydantic AI via MCP:

cora_cancel_invoice

Cancela uma cobrança (Invoice) pendente do Banco Cora

cora_create_invoice

Criar uma Cobrança Oficial (Boleto bancário + QR Code Pix) (Cora Bank)

cora_get_balance

Traz todos os recursos atuais parados ou pendentes no Cora Bank. Consulta de recursos retidos totais (Balanço / Saldo)

cora_get_invoice

Consultar os dados ou status detalhado de uma Fatura/Cobrança

cora_get_statement

Extração de histórico contábil, recebimentos e extrato de cashflow

cora_list_invoices

Lista em massa faturas/boletos e verifica seus resultados

cora_list_payments

Consultar um array contendo os retiros efetuados da sua base ou conta

cora_send_pix

Efetuar envio de TED ou Pix pagando Fornecedor ou Cliente

Example Prompts for Cora Bank in Pydantic AI

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

"Draw up a Cora Invoice for client Gabriel (CPF 908129841). Bill them exactly R$ 150 BRL for the 'Graphic Design Package' with due date at the end of next month."

"Fetch the final Cora Account statement focusing from 2024-04-01 until 2024-04-06 to ensure we captured all vendor payouts."

"Cancel the Cora pending invoice reference 'INV_17009401' completely. We negotiated an upfront cash structure."

Troubleshooting Cora Bank MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Cora Bank + Pydantic AI FAQ

Common questions about integrating Cora Bank 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 Cora Bank MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.