How to Use the BCB Juros — Selic, CDI e Expectativas Focus MCP in LangChain

Build financial reasoning pipelines in LangChain using live Brazilian interest rates and market forecasts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BCB Juros — Selic, CDI e Expectativas Focus MCP to LangChain

Create your Vinkius account to connect BCB Juros — Selic, CDI e Expectativas Focus 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 Juros — Selic, CDI e Expectativas Focus with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

ReAct agents for Brazilian fixed income

Your ReAct agents need actual numbers to make decisions about Brazilian assets. Giving them direct access to `get_cdi` lets the agent pull the exact interbank deposit certificate rate used to benchmark CDBs and LCIs. The agent checks the daily rate, compares it to your internal database, and decides the next move in the chain. Multi-step reasoning works best when the inputs are precise. You can build a pipeline where the agent first calls `get_selic_meta` to grab the COPOM target rate. It then passes that value into a custom calculator tool you wrote, generating a yield projection without hardcoding yesterday's news.

Track every MCP Server call in LangSmith

Financial applications demand strict observability. Every time your chain requests the daily effective Selic rate via `get_selic_diaria`, LangSmith logs the exact transport latency and token usage. You see exactly what the model asked the BCB API and what JSON payload came back. Debugging hallucinated interest rates is a nightmare. Tracing these tool calls proves your agent is grounding its answers in real SGS series 11 data. You get a clear audit trail showing how the agent arrived at its final investment recommendation.

Chain market forecasts into your logic

The Focus Report drops every Monday with fresh market projections. You can wire `get_expectativas_selic` into a scheduled LangChain pipeline that runs right after the central bank publishes. The tool returns the median, mean, minimum, and maximum expectations from top financial institutions. That output becomes the input for your next chain link. A summarization prompt takes those numbers, drafts a risk report, and fires it off to your Slack channel. Your system reacts to macroeconomic shifts automatically.

Setup guide

Set up BCB Juros — Selic, CDI e Expectativas Focus 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 Juros — Selic, CDI e Expectativas Focus 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-juros-selic-cdi-e-expectativas-focus-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 Juros — Selic, CDI e Expectativas Focus 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 Juros — Selic, CDI e Expectativas Focus 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 Juros — Selic, CDI e Expectativas Focus MCP in LangChain

Install langchain-mcp-adapters. Initialize a MultiServerMCPClient pointing to the Vinkius endpoint, call client.get_tools(), and pass the list directly to your agent constructor.

The current tools fetch the latest available rates and expectations. Your agent calls get_cdi or get_selic_meta to get the current benchmark, which you can then store in your own vector database for historical comparison.

Yes. Your ReAct agent can pull the COPOM target rate using this server and then query your internal Postgres database to find portfolios underperforming that benchmark.

The Central Bank publishes the Focus Survey every Monday. Calling get_expectativas_selic fetches those weekly projections straight from the source.

Vinkius runs the server in an ephemeral V8 Isolate Sandbox. Your agent requests public macroeconomic indicators like the CDI rate, and the server fetches them. No customer prompts or internal chain logic are logged, stored, or inspected by the sandbox.

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