How to Use the BCB Full — Inteligência Financeira Completa do Brasil MCP in AutoGen

Q: How do I set up BCB Full — Inteligência Financeira Completa do Brasil in AutoGen?

Run pip install -U "autogen-extmcp". Use mcpservertools with a StreamableHttpServerParams object to fetch the tools. Pass that list into your AssistantAgent constructor.

Q: How do the AutoGen agents handle the Focus report data?

They call getexpectativasselic to get the median, mean, and extreme projections. A conservative agent might focus on the maximum projection, while an aggressive agent argues based on the minimum, driving a data-backed negotiation.

Q: Does the MCP server support historical commercial dollar rates?

The getdolarsgs tool provides long-term historical series for the commercial dollar. Agents can specify exact dates in DD/MM/YYYY format to pull specific historical quotes for their economic models.

Build debating financial agents powered by Brazilian Central Bank data in AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BCB Full — Inteligência Financeira Completa do Brasil MCP to AutoGen

Create your Vinkius account to connect BCB Full — Inteligência Financeira Completa do Brasil to AutoGen 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 Full — Inteligência Financeira Completa do Brasil with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Macroeconomic Debate

`get_selic_meta` and `get_ipca` provide the raw facts for your AutoGen agents to argue over. A hawkish monetary agent can pull the current inflation data while a dovish agent fetches the unemployment rate via `get_desemprego`. They debate the economic outlook based on hard numbers, challenging each other's conclusions until they reach a consensus. The framework handles the back-and-forth automatically. One agent might point out rising inflation expectations using `get_expectativas_inflacao`, prompting another to check the trade balance with `get_balanca_comercial`. You build systems where competing perspectives analyze the Brazilian economy using official Central Bank statistics.

Currency and Exchange Rate Analysis

`get_cotacao_dolar` feeds official PTAX buy and sell rates into your conversation group. An import-export agent can request the current dollar quote, while a risk management agent pulls historical volatility using `get_dolar_periodo`. They negotiate the best time to execute a hypothetical trade based on the data. The system supports over 150 global currencies through `get_cotacao_moeda`. If an agent proposes a trade in Chilean Pesos, a validation agent can first run `listar_moedas` to confirm the exact currency code. `McpToolAdapter` handles all the schema conversions behind the scenes, so the agents just focus on the financial strategy.

Deep Statistical Access via MCP Server

`get_serie_bcb` exposes 20,000 time series for your AutoGen deliberation groups. An agent tasked with assessing fiscal health can pull the public debt ratio via `get_divida_pib`. Another agent can counter by pulling international reserve levels with `get_reservas`, sparking a detailed discussion about sovereign risk. You configure this by passing the server URL to `mcp_server_tools` and handing the list to your `AssistantAgent`. The agents can also track the adoption of instant payments by calling `get_pix_estatisticas`. The conversation continues until the agents agree on the economic impact of the transaction volumes.

Setup guide

Set up BCB Full — Inteligência Financeira Completa do Brasil MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes BCB Full — Inteligência Financeira Completa do Brasil tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="BCB Full — Inteligência Financeira Completa do Brasil_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent BCB Full — Inteligência Financeira Completa do Brasil data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="BCB Full — Inteligência Financeira Completa do Brasil_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent BCB Full — Inteligência Financeira Completa do Brasil data")
    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 Full — Inteligência Financeira Completa do Brasil 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 Full — Inteligência Financeira Completa do Brasil MCP in AutoGen

Run `pip install -U "autogen-ext[mcp]"`. Use `mcp_server_tools` with a `StreamableHttpServerParams` object to fetch the tools. Pass that list into your `AssistantAgent` constructor.

Any agent in the conversation group equipped with the tools can invoke them. One agent might pull `get_cdi` while another fetches `get_igpm`, and they will share the results in the chat history.

They call `get_expectativas_selic` to get the median, mean, and extreme projections. A conservative agent might focus on the maximum projection, while an aggressive agent argues based on the minimum, driving a data-backed negotiation.

The `get_dolar_sgs` tool provides long-term historical series for the commercial dollar. Agents can specify exact dates in DD/MM/YYYY format to pull specific historical quotes for their economic models.

The tools interact with public metrics like the INPC inflation index and PIX transaction counts. Vinkius routes these requests through a stateless V8 sandbox environment. Your agent's internal debate history and specific tool parameters vanish the moment the session ends.

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