How to Use the Maranhão Open Data MCP in Google ADK

Q: How do I configure Maranhão Open Data with Google ADK?

Install google-adk and create an McpToolset using your Vinkius HTTP endpoint. Pass that toolset to your LlmAgent tools array. It works over standard HTTP transport.

Q: Can Google ADK filter the Maranhão Open Data tools?

Absolutely. You can use the toolnames parameter when initializing the toolset. This lets you expose searchdatastoresql to an analyst agent while restricting a public-facing agent to just searchpackages.

Give Google ADK agents native access to Maranhão Open Data. Query Brazilian public records directly alongside your BigQuery warehouse.

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 Google ADK

Create your Vinkius account to connect Maranhão Open Data to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search Brazilian public records via MCP

Finding specific public data usually means clicking through broken government portals. You can skip that entirely. Your Gemini agent uses `search_packages` to hunt down Maranhão datasets by keyword. If you are doing a massive ingestion job into Google Cloud, you just have the agent run `list_packages`. It pulls the entire catalog index. Gemini's massive context window easily holds the full list, letting the agent plan which datasets to process next.

Execute SQL via Google ADK

The real power here is direct database access. Your agent does not have to download CSVs to analyze them. It uses `search_datastore_sql` on the MCP Server to fire relational queries directly at the Maranhão DataStore. Your agent aggregates demographics or budget numbers on the fly. If the task is simpler, it uses `search_datastore` for basic filtering. The results feed straight back into your Gemini workflow for immediate reasoning.

Extract precise resource metadata

Datasets are useless if you don't know the file formats. Your agent calls `get_package` to grab the high-level metadata, then loops through `get_resource` to inspect the actual files. It finds out exactly where the CSVs and APIs live. You can then pipe those endpoints straight into Vertex AI or write an ingestion script to dump the raw files into BigQuery.

Setup guide

Set up Maranhão Open Data MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Maranhão Open Data tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Maranhão Open Data_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Maranhão Open Data tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install `google-adk` and create an `McpToolset` using your Vinkius HTTP endpoint. Pass that toolset to your `LlmAgent` tools array. It works over standard HTTP transport.

Absolutely. You can use the `tool_names` parameter when initializing the toolset. This lets you expose `search_datastore_sql` to an analyst agent while restricting a public-facing agent to just `search_packages`.

Gemini's 1M+ token context window swallows large metadata dumps easily. When your agent runs `list_packages`, it can process the entire catalog response without memory errors.

Not natively through the MCP Server. Your agent uses the tools to fetch the Maranhão data, then you use Google ADK's native BigQuery features to merge it with your internal tables.

The server only accesses public Brazilian municipal datasets. Since Vinkius handles the isolated sandbox, your Google Cloud environment never directly executes untrusted code. Just be aware that any search terms your agent generates are sent to the public portal.

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