How to Use the Maranhão Open Data MCP in LangChain

Q: How do I run SQL queries on Maranhão Open Data using LangChain?

Use the searchdatastoresql tool within your LangChain agent's toolset. The agent writes a standard SQL query, runs it against the Maranhão datastore, and passes the raw tabular results directly into your chain's next step.

Q: Can a LangChain agent search for specific Maranhão Open Data packages?

Yes, the agent can use the searchpackages tool to find datasets matching specific keywords like education or finance. This lets your LangChain pipeline search the Maranhão registry dynamically instead of hardcoding dataset IDs.

Run multi-step reasoning chains over Maranhão Open Data using LangChain agents to query Brazilian public records.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Maranhão Open Data MCP to LangChain

Create your Vinkius account to connect Maranhão Open Data 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 Maranhão Open Data with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run SQL queries on Maranhão Open Data via LangChain

The `search_datastore_sql` tool lets your LangChain agent execute raw SQL queries directly against the Maranhão state database. This means your chain can run complex aggregations or filter public records on the fly without pulling down giant datasets first. LangChain handles this by feeding the schema from `get_package` into the prompt, letting the model write precise queries. You can track the exact SQL execution latency and token usage inside LangSmith to keep your data pipelines fast and cheap.

Discover Brazilian public datasets in LangChain pipelines

The `list_packages` tool acts as the entry point for your LangChain agent to browse all available public registries in the Maranhão portal. Instead of guessing dataset names, your agent dynamically retrieves the full catalog to find the exact tables it needs. Once the agent finds a candidate, it calls `get_package` to inspect the metadata and verify the schema. This multi-step discovery process runs entirely within a single ReAct loop, letting your chain adapt to new datasets as the state government publishes them.

Extract specific CSV data with this MCP Server

The `get_resource` tool lets your LangChain chain target and retrieve specific files, like CSVs or API endpoints, nested within a Maranhão dataset. Your agent can isolate the exact file ID it needs based on metadata search results rather than parsing the entire package. By combining this with `search_datastore`, the agent filters the resource contents before passing them to the next chain link. This keeps your context window clean because you only load the relevant rows into your model's memory using this MCP Server.

Setup guide

Set up Maranhão Open Data 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 Maranhão Open Data 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({
    "maranhao-open-data-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 Maranhão Open Data 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 Maranhão 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 Maranhão Open Data 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 Maranhão Open Data MCP in LangChain

Use the `search_datastore_sql` tool within your LangChain agent's toolset. The agent writes a standard SQL query, runs it against the Maranhão datastore, and passes the raw tabular results directly into your chain's next step.

Yes, the agent can use the `search_packages` tool to find datasets matching specific keywords like education or finance. This lets your LangChain pipeline search the Maranhão registry dynamically instead of hardcoding dataset IDs.

Avoid pulling the whole dataset. Have your LangChain agent use `search_datastore` to filter rows by specific keys, or use `search_datastore_sql` to run aggregations directly on the server before returning the data.

The server is stateless by default. If you need to maintain context across multiple steps, use the LangChain MCP adapter's client session handler to keep the connection active.

Your SQL queries and metadata requests go straight to the Maranhão CKAN API through a secure, ephemeral V8 sandbox. Vinkius handles the endpoint token, meaning your database parameters and raw Brazilian public records are never stored or logged.

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