How to Use the MDIC (Comércio Exterior) MCP in LangChain

Q: How do I query MDIC (Comércio Exterior) datasets using LangChain?

Use searchdatastore inside your chain. The adapter exposes this tool directly to your agent, letting it execute SQL-like queries and pass the raw trade data to subsequent steps.

Q: Can LangChain handle schema changes in the MDIC (Comércio Exterior) portal?

Yes. Your agent can call getresource first to inspect the current file structure. This lets you build dynamic chains that adapt to changes in the Brazilian trade data formats.

Q: What is the best way to search for specific trade years in MDIC (Comércio Exterior) using LangChain?

Have your agent use searchpackages with specific terms like exportação 2023. Once it locates the package, it can list the files and query them immediately.

Feed real-time Brazilian trade data directly into your LangChain reasoning loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MDIC (Comércio Exterior) MCP to LangChain

Create your Vinkius account to connect MDIC (Comércio Exterior) 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 MDIC (Comércio Exterior) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pull live customs data into your chain

The `search_datastore` tool pulls raw import and export statistics directly from Brazilian government databases. Your agent can run SQL-like queries on specific resource IDs without downloading massive CSV files first. Because LangChain handles multi-step chains, you can feed these raw statistics straight into a calculation step. It cuts out the manual data cleaning phase entirely.

Discover Brazilian trade datasets via LangChain

The `search_packages` and `list_packages` tools let your agent hunt down specific trade datasets using simple search terms. It checks the entire MDIC catalog to locate the exact data files you need. You don't have to guess the dataset names or IDs beforehand. This MCP Server lets your chain inspect the metadata via `get_package` and select the correct resource automatically before running any deep analysis.

Inspect file metadata before downloading

The `get_resource` tool inspects specific data file structures and formats before your chain attempts to parse them. It checks the schema, file type, and update frequency directly from the MDIC endpoint. This keeps your pipelines from crashing on unexpected format shifts. If the schema changes, your agent catches it early and adjusts its parsing logic on the fly.

Setup guide

Set up MDIC (Comércio Exterior) 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 MDIC (Comércio Exterior) 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({
    "mdic-comercio-exterior-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 MDIC (Comércio Exterior) 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 MDIC (Comércio Exterior). 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 MDIC (Comércio Exterior) 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 MDIC (Comércio Exterior) MCP in LangChain

Use `search_datastore` inside your chain. The adapter exposes this tool directly to your agent, letting it execute SQL-like queries and pass the raw trade data to subsequent steps.

Yes. Your agent can call `get_resource` first to inspect the current file structure. This lets you build dynamic chains that adapt to changes in the Brazilian trade data formats.

Have your agent use `search_packages` with specific terms like exportação 2023. Once it locates the package, it can list the files and query them immediately.

Use the LangChain MCP adapter to connect to the Vinkius endpoint. It exposes all five trade tools to your model in a single initialization step.

Your queries go directly to the official Brazilian government endpoints via our secure sandbox. We do not store or cache the trade statistics or package metadata your agent pulls.

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