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

Index live Brazilian economic data directly into your LlamaIndex RAG applications using this MCP Server.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground RAG Queries in Live BCB Data via MCP Server

Hallucinations destroy financial analysis. Connecting LlamaIndex to this server lets your system pull actual public debt ratios via `get_divida_pib` before answering user queries. The agent retrieves the current fiscal sustainability metric and injects it straight into your context window. This creates a factual baseline for your documents. When a user asks about Brazil's economic health, LlamaIndex hits `get_pib` for the latest IBC-Br proxy. It then synthesizes that hard data with your internal market reports, ensuring every response relies on actual Central Bank figures.

Index PIX and Trade Stats for Semantic Search

Static PDFs about the Brazilian market get outdated fast. You can use LlamaIndex to pull live transaction volumes using `get_pix_estatisticas` and store the results in your vector database. The system then queries `get_balanca_comercial` to grab the latest commodity export surplus. Your knowledge base becomes a living entity. As LlamaIndex pulls these metrics, it embeds them alongside your historical research. Analysts can run semantic searches across both your proprietary insights and the exact dollar amounts of Brazil's international trade balance.

Expand Your Knowledge Base with 20,000+ Series

Standard endpoints only cover the basics. The `get_serie_bcb` MCP tool gives your LlamaIndex setup access to the entire Sistema Gerenciador de Séries Temporais. You can pull the Selic interest rate or IPCA inflation numbers and index them instantly. Combining this with specific tools like `get_reservas` gives your RAG application massive depth. The agent checks the international reserves in USD, then searches the broader SGS database for correlating currency fluctuations. All of this data gets chunked, embedded, and made ready for natural language querying.

Filter Tools for Specific Agent Roles

Not every query engine needs access to the entire Central Bank database. You can restrict your LlamaIndex setup using the allowed tools filter. A specific labor market agent gets access to `get_desemprego`, while the general macro agent handles the broader indicators. This targeted approach keeps your agents focused. They spend fewer tokens deciding which tool to call and return answers faster. You maintain tight control over which endpoints feed into your vector index.

Setup guide

Set up BCB Economia — PIB, Dívida, Reservas, PIX e SGS MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all BCB Economia — PIB, Dívida, Reservas, PIX e SGS MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to BCB Economia — PIB, Dívida, Reservas, PIX e SGS tools.",
)
response = await agent.run("List recent BCB Economia — PIB, Dívida, Reservas, PIX e SGS data")

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 LlamaIndex

Install the llama-index-tools-mcp package. Set up a BasicMCPClient with your Vinkius endpoint, wrap it in an McpToolSpec, and call the async tool list generator to feed your FunctionAgent.

Yes. When the agent calls a tool, the resulting JSON is returned to the query engine. You can configure your RAG pipeline to embed these live responses alongside your existing document vectors.

Use the allowed tools filter when initializing the tool spec. You might want to restrict a specific agent to only pull unemployment stats while blocking access to the broader custom series endpoint.

The tool returns the raw percentage variations. You should add context in your LlamaIndex system prompt explaining that IBC-Br is a monthly predictor for the official quarterly GDP.

Data security is strictly enforced at the infrastructure level. The Vinkius V8 sandbox handles the external MCP Server request to pull the time series data. Your proprietary LlamaIndex documents and query embeddings never leave your local environment or get sent to the Central Bank.

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