How to Use the Conta Azul MCP in LangChain

Q: How do I handle Conta Azul customer lookups in LangChain?

Use the searchcustomers tool inside a LangGraph routing node. The agent inspects the returned CPF or CNPJ data to determine whether to update or create a profile.

Q: Can my LangChain agent reconcile bank accounts using Conta Azul?

Yes, the agent calls listbankaccounts to pull live balances. It then matches those figures with sales records retrieved via listsales in the same execution chain.

Q: How do I configure LangChain to connect to Conta Azul?

Install the required MCP adapter with pip install langchain-mcp-adapters langgraph first. Then, instantiate the MultiServerMCPClient pointing to your Vinkius endpoint and pass the tools to your agent.

Run LangChain agents that write Brazilian invoices and update ERP records directly inside your multi-step chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Conta Azul MCP to LangChain

Create your Vinkius account to connect Conta Azul to LangChain 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 Conta Azul with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated customer syncing in LangChain

The `create_customer` tool injects new corporate or individual fiscal records directly into your Brazilian ERP during active agent runs. Your LangChain agent uses this tool to register buyers on the fly before initiating any billing steps. It extracts tax IDs from incoming emails and formats them for the ERP without manual data entry. You trace the entire execution path using LangSmith to spot exactly when `search_customers` runs to verify existing records. If the customer isn't found, the chain automatically routes the payload to the creation step. This stops duplicate accounts. It keeps your pipeline clean.

Chain-linked billing with this MCP Server

The `create_product` tool maps physical goods and assigns their values in Brazilian Real within your automated workflow. Your LangChain agent feeds the output of this tool directly into `create_service` to build hybrid invoices. No manual copying. The next step in the chain consumes the raw JSON output immediately. This MCP Server handles the complex Conta Azul payload mapping so your agent can focus on deciding the next logical step. You monitor the exact token usage and latency of these Conta Azul financial updates through your LangSmith dashboard.

Real-time contract and bank audits

The `list_bank_accounts` tool retrieves current cash positions and matches them against active billing records in your ERP. Your LangChain agent runs this check alongside `list_contracts` to flag accounts that are past due. It evaluates payment histories without requiring you to write custom integration glue. By chaining these MCP tools, the agent determines which clients require immediate follow-up. The entire process runs inside stateless execution blocks, but you can spin up persistent sessions when tracking multi-step audits.

Setup guide

Set up Conta Azul MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Conta Azul tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "conta-azul-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Conta Azul transactions"
    })
    print(result["messages"][-1].content)

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 Conta Azul. 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 Conta Azul 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 Conta Azul MCP in LangChain

Use the `search_customers` tool inside a LangGraph routing node. The agent inspects the returned CPF or CNPJ data to determine whether to update or create a profile.

Yes, the agent calls `list_bank_accounts` to pull live balances. It then matches those figures with sales records retrieved via `list_sales` in the same execution chain.

Install the required MCP adapter with `pip install langchain-mcp-adapters langgraph` first. Then, instantiate the `MultiServerMCPClient` pointing to your Vinkius endpoint and pass the tools to your agent.

Install the library, instantiate the client, and load the tools. You can then register them directly within your LangGraph workflow or standard chain adapter.

Your CPF, CNPJ, and financial transaction records pass through an ephemeral, zero-trust V8 sandbox. Vinkius never stores these ERP payloads, meaning your sensitive fiscal data is destroyed as soon as the session closes.

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