How to Use the Minas Gerais (Estado) MCP in LangChain

Q: How do I pull a list of all state departments?

Use the listorganizations tool within your agent's toolbelt. It queries the live CKAN backend of the state of Minas Gerais and returns the unique identifiers for every registered public agency.

Build LangChain reasoning chains that query, filter, and extract public datasets directly from the Minas Gerais (Estado) open data portal.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Minas Gerais (Estado) MCP to LangChain

Create your Vinkius account to connect Minas Gerais (Estado) 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 Minas Gerais (Estado) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Minas Gerais (Estado) queries in LangChain

Your LangChain agent can now run multi-step chains that pull directly from Brazilian state records. By combining `list_organizations` to find departments with `search_packages`, your pipeline dynamically isolates target government datasets without manual lookup. The output from one tool feeds directly into the next step of your chain. This setup lets you build autonomous data pipelines that extract specific resource links. For example, your agent can run `get_package` on a discovered dataset and immediately pass the resulting file URLs to a downloader node in your LangChain graph.

Track Minas Gerais (Estado) MCP Server calls in LangSmith

Debugging public data queries gets simple when you monitor every tool call. When your agent uses `search_resources` or `list_groups` to browse Minas Gerais (Estado) records, LangSmith captures the exact parameters and JSON payloads. You see the latency of the state's CKAN API in real-time. This visibility helps you optimize how your LangChain chains interact with the state's infrastructure. If a query using `get_resource` runs slow, you can adjust your agent's prompt or add caching to prevent hitting the state portal too hard.

Multi-agent routing for state data

Set up a LangGraph workflow where different agents handle different parts of the Minas Gerais (Estado) catalog. One agent can specialize in categorization by using `list_tags` and `get_group`, while another focuses on deep metadata parsing using `get_package`. They pass state-specific context back and forth using standard LangChain state management. This keeps your agents focused on small, reliable tasks instead of trying to parse the entire Brazilian state repository in a single run.

Setup guide

Set up Minas Gerais (Estado) 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 Minas Gerais (Estado) 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({
    "minas-gerais-estado-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 Minas Gerais (Estado) 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 Minas Gerais Open Data. 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 Minas Gerais (Estado) 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 Minas Gerais (Estado) MCP in LangChain

You configure your LangChain agent with this MCP Server and call `search_packages` with a query like "meio ambiente". The server returns matching metadata packages directly from the state's database, which your agent can then parse or pass to subsequent chains.

Yes, you can filter the toolset during initialization. When calling `client.get_tools()` from the MCP adapter, simply pass a filtered list containing only specific tools like `get_resource` or `list_organizations` to your LangChain agent.

The MCP Server passes the error up to your LangChain chain, which you can handle using standard LangGraph retry policies. This is especially useful for tools like `search_resources` that might query large state datasets under heavy load.

Use the `list_organizations` tool within your agent's toolbelt. It queries the live CKAN backend of the state of Minas Gerais and returns the unique identifiers for every registered public agency.

Yes, because this integration only reads public CKAN metadata and resource URLs from the state's server. Your private local data never goes to the Brazilian state portal; the MCP Server runs in a sandboxed V8 isolate that only transmits public search parameters to the open data API.

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