How to Use the BCB Economia — PIB, Dívida, Reservas, PIX e SGS MCP in LangChain

Build multi-step economic reasoning pipelines in LangChain using live Brazilian Central Bank data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BCB Economia — PIB, Dívida, Reservas, PIX e SGS MCP to LangChain

Create your Vinkius account to connect BCB Economia — PIB, Dívida, Reservas, PIX e SGS 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 BCB Economia — PIB, Dívida, Reservas, PIX e SGS with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Brazilian Macro Indicators in LangChain

ReAct agents need sequential data to make sense of emerging markets. You give your LangChain agent access to `get_pib` and `get_desemprego`, and it decides the order of operations. It pulls the IBC-Br monthly GDP proxy, evaluates the trend, and conditionally triggers the unemployment rate fetch based on the first result. This sequential logic turns raw endpoints into actual economic analysis. Instead of dumping numbers into a prompt, your agent chains `get_divida_pib` directly into a vector store lookup for historical context. You track every token and latency spike through LangSmith tracing while the agent builds a complete fiscal picture of Brazil.

Map PIX Payment Velocity to Trade Balance

Brazil runs on PIX. Your LangChain pipelines can hit `get_pix_estatisticas` to track domestic transaction volumes in real time. The agent then pulls the export surplus via `get_balanca_comercial` to compare internal liquidity against external commodity flows. Passing these outputs between chain links creates a dynamic view of the Brazilian economy. The agent evaluates the trade balance first, formats the output, and feeds it as the prompt context for the PIX volume analysis. You control the entire flow with standard LangChain composability.

Query 20,000+ Custom SGS Series via MCP

Hardcoding specific indicators limits your agent's reasoning. The `get_serie_bcb` tool lets your LangChain setup query any of the 20,000+ time series from the Central Bank's SGS database dynamically. If the agent needs the Selic rate (11) or inflation (IPCA 433), it just asks for the code. Multi-step pipelines thrive on this flexibility. The agent starts with a broad query for international reserves using `get_reservas`. If it detects a drop, it automatically calls the custom SGS MCP tool to pull the USD exchange rate (SGS code 1) to check for currency intervention, all within a single execution trace.

Validate Outputs with Built-in Guardrails

Financial data requires strict formatting before it hits your downstream apps. You can wrap the `get_pib` output in a LangChain Pydantic parser to guarantee the agent returns a valid float for the GDP percentage variation. The system catches bad parsing immediately and forces the agent to retry the tool call. This keeps your pipelines from crashing when the Central Bank updates an indicator format. The agent handles the error, adjusts its parsing strategy, and re-runs the specific tool without breaking the entire chain.

Setup guide

Set up BCB Economia — PIB, Dívida, Reservas, PIX e SGS 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 BCB Economia — PIB, Dívida, Reservas, PIX e SGS 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({
    "bcb-economia-pib-divida-reservas-pix-e-sgs-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 BCB Economia — PIB, Dívida, Reservas, PIX e SGS 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 Banco Central do Brasil. 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 BCB Economia — PIB, Dívida, Reservas, PIX e SGS 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 BCB Economia — PIB, Dívida, Reservas, PIX e SGS MCP in LangChain

Install the langchain-mcp-adapters package. Initialize a MultiServerMCPClient pointing to your Vinkius HTTP URL. Call the tool fetch method and pass the resulting array directly into your ReAct agent setup.

Yes. LangSmith automatically logs every tool invocation. You see the exact SGS codes the agent requested and the raw JSON payload returned by the Central Bank API.

You need to provide the codes in your system prompt or a connected vector store. The agent can then pass those specific integers into the custom series tool to pull the exact historical data.

The Vinkius infrastructure manages the connection to the Central Bank. You just need to add standard retry logic or fallback chains in your LangGraph setup to handle occasional upstream timeouts.

Privacy matters when dealing with macro analysis. This server only pulls public economic indicators like GDP and PIX volumes from the Brazilian Central Bank. Vinkius runs the connection in an ephemeral V8 Isolate sandbox, meaning your specific chain inputs and indicator queries vanish the moment the HTTP request finishes.

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