How to Use the BrasilAPI MCP in LlamaIndex

Q: Can I index the output of BrasilAPI calls for semantic search?

Yes, you can take the JSON returned by getcnpjdetails and insert it into a vector index. This lets your LlamaIndex pipeline search through Brazilian company profiles using natural language.

Q: Does the BrasilAPI integration support asynchronous tool execution in LlamaIndex?

It does, allowing you to fetch vehicle prices via getfipevehicleprice and state lists asynchronously. This keeps your query pipelines fast when dealing with multiple concurrent requests.

Index Brazilian corporate data, CEP lookups, and FIPE vehicle prices directly into your LlamaIndex RAG pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BrasilAPI MCP to LlamaIndex

Create your Vinkius account to connect BrasilAPI 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 BrasilAPI with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Brazilian company records for LlamaIndex RAG

Pull active corporate registries via `get_cnpj_details` and index them directly into your vector store. Your agent can query this knowledge base later to answer complex questions about Brazilian business structures without hitting the live API repeatedly. This MCP Server feeds clean JSON payloads into your indexers, preventing formatting issues during chunking. When your agent needs to verify a company, it searches the local index first before deciding to trigger a live API call.

Store and query localized CEP address data

Resolve postal codes with `get_cep_details` and store the geographic coordinates or street data in your document store. LlamaIndex uses this indexed address history to ground its responses, ensuring your agent doesn't hallucinate Brazilian neighborhoods. You can combine these lookups with `list_brazilian_states` to build a localized knowledge graph of regional operations. The agent queries this graph to find out which states contain specific postal code clusters.

Build vehicle valuation indexes using FIPE data

Retrieve vehicle pricing trends using `get_fipe_vehicle_price` and turn those market values into searchable vector embeddings for your MCP client. Your agent can run semantic searches across different car models to find pricing anomalies or average valuations. By indexing these prices alongside the list of institutions from `list_brazilian_banks`, you create a detailed auto finance database. The agent retrieves matches from this combined vector space to answer complex lending questions.

Setup guide

Set up BrasilAPI 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 BrasilAPI 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 BrasilAPI tools.",
)
response = await agent.run("List recent BrasilAPI 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 BrasilAPI. 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 BrasilAPI 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 BrasilAPI MCP in LlamaIndex

Use the LlamaIndex MCP tool spec to connect to the Vinkius URL, then convert the server tools to a list. Pass that list to your FunctionAgent to let it run lookups like `get_cep_details` automatically.

Yes, you can take the JSON returned by `get_cnpj_details` and insert it into a vector index. This lets your LlamaIndex pipeline search through Brazilian company profiles using natural language.

It does, allowing you to fetch vehicle prices via `get_fipe_vehicle_price` and state lists asynchronously. This keeps your query pipelines fast when dealing with multiple concurrent requests.

You can use the allowed tools filter when initializing the client to expose only specific endpoints. If you only want your agent to handle address verification, you can limit it to `get_cep_details`.

Your requests for corporate registries and address details pass through an encrypted connection to the API. The Vinkius MCP Server runtime executes the tool in an ephemeral container, ensuring no Brazilian tax IDs or postal codes are cached on the server.

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