How to Use the Maranhão Open Data MCP in OpenAI Agents SDK

Q: How do I connect Maranhão Open Data to OpenAI Agents SDK?

Install openai-agents via pip. Initialize MCPServerStreamableHttp with the Vinkius URL and pass it to your Agent constructor's mcpservers array. The agent auto-discovers the tools immediately.

Q: Can the agent execute SQL against Maranhão Open Data with OpenAI Agents SDK?

Yes. The server exposes searchdatastoresql. Your agent writes the query, and the SDK's guardrails validate the action before sending it to the Brazilian data portal.

Q: Does the OpenAI Agents SDK cache the Maranhão Open Data MCP tools?

It does if you tell it to. Set cacheToolsList=True during setup. This skips the discovery phase on subsequent runs and speeds up your agent's response time.

Connect OpenAI Agents SDK to Maranhão public records. Build production agents with built-in guardrails and direct SQL access.

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 OpenAI Agents SDK

Create your Vinkius account to connect Maranhão Open Data to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Discover Brazilian datasets with OpenAI Agents SDK

You need public records from Maranhão, and you want your agent to find them without hallucinating endpoints. Using `search_packages`, your agent queries the portal by keyword to locate relevant datasets. If it needs a broad overview, it runs `list_packages` to enumerate everything available on the server. Once the agent identifies a dataset, it calls `get_package` to pull the exact metadata. Because this happens inside the OpenAI ecosystem, every step is traced. You can watch the agent narrow down its search in the dashboard before it actually touches the raw data.

Query the datastore with raw SQL

Pulling entire datasets into memory is a waste of compute. This MCP Server gives your agent direct database access. The `search_datastore_sql` tool lets your agent write and execute relational queries right against the Maranhão DataStore. If you do not need a complex join, the agent drops back to `search_datastore` for simple key-value filtering. You define the guardrails. The agent decides which query method fits the task, and OpenAI validates the action before execution.

Inspect resource metadata instantly

Before your agent downloads a massive file, it needs to know what it is looking at. The `get_resource` tool fetches the specifics of an individual file or API endpoint within a package via this MCP connection. It tells your system whether it is dealing with a CSV, a JSON feed, or a dead link. You build handoffs based on this response. Send the CSVs to an analysis agent and route the APIs to a scraper, all automatically.

Setup guide

Set up Maranhão Open Data MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Maranhão Open Data tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Maranhão Open Data tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Maranhão Open Data tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Maranhão Open Data Agent",
            instructions="You have access to Maranhão Open Data tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip. Initialize `MCPServerStreamableHttp` with the Vinkius URL and pass it to your Agent constructor's `mcp_servers` array. The agent auto-discovers the tools immediately.

Yes. The server exposes `search_datastore_sql`. Your agent writes the query, and the SDK's guardrails validate the action before sending it to the Brazilian data portal.

It does if you tell it to. Set `cacheToolsList=True` during setup. This skips the discovery phase on subsequent runs and speeds up your agent's response time.

The SDK catches the error and logs it in your OpenAI dashboard tracing. Your agent can then decide to retry with a different `search_packages` keyword or alert you.

This server only reads public Brazilian government records and metadata. However, you are sending raw SQL queries and search terms to an external government portal. Ensure your agent prompts do not inadvertently mix internal company data into the `search_datastore_sql` parameters.

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