How to Use the Minas Gerais (Estado) MCP in Google ADK

Q: How do I configure the Minas Gerais (Estado) MCP Server tools in google-adk?

Instantiate McpToolset with the server's HTTP endpoint in your Python code. Google ADK registers the tools, allowing your Gemini agent to run searchpackages and getpackage directly.

Q: Can I restrict a google-adk agent to only search specific Minas Gerais (Estado) categories?

Yes, you can use the toolnames filter in Google ADK to expose only specific tools like listgroups or searchresources. This prevents the agent from calling other administrative endpoints on the Minas Gerais (Estado) portal.

Q: How do I combine Minas Gerais (Estado) public data with BigQuery using google-adk?

Your agent runs getresource via the Google ADK to locate the file URL, then uses Google Cloud client libraries to load that file into BigQuery. The agent automates the transfer, letting you query the state's public data alongside your internal datasets.

Feed Minas Gerais (Estado) MCP Server datasets into Gemini's long-context window using the Google ADK framework.

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 Google ADK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed State Datasets into Gemini Long Context

`list_packages` and `get_package` pull extensive public metadata from the Minas Gerais (Estado) portal. The Google ADK uses this MCP integration to pull public metadata directly into Gemini's million-token context window. Your agent processes entire organizational structures retrieved via `list_organizations` without hitting token limits. This allows deep thematic analysis of Brazilian public administration data directly within Vertex AI.

Analyze Minas Gerais (Estado) MCP Server Data in BigQuery

This MCP Server works alongside your Google Cloud data pipelines to bridge public APIs and enterprise storage. Your Google ADK agent fetches state records using `get_resource` and prepares them for loading into BigQuery tables. By combining public datasets with your private enterprise tables, you run SQL queries on freshly pulled government data. The agent coordinates the entire retrieval and staging process.

Target Specific State Groups and Tags

`list_groups` and `list_tags` allow your agent to filter Minas Gerais (Estado) datasets before executing heavy analytical queries. This pre-filtering minimizes API overhead and keeps your Google ADK agent focused on relevant data subsets. The agent uses `search_packages` to pinpoint specific public files, avoiding unnecessary document processing. Running queries this way keeps your Vertex AI token usage highly efficient.

Setup guide

Set up Minas Gerais (Estado) 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 Minas Gerais (Estado) 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="Minas Gerais (Estado)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Minas Gerais (Estado) 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 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 Google ADK

Instantiate `McpToolset` with the server's HTTP endpoint in your Python code. Google ADK registers the tools, allowing your Gemini agent to run `search_packages` and `get_package` directly.

Yes, you can use the `tool_names` filter in Google ADK to expose only specific tools like `list_groups` or `search_resources`. This prevents the agent from calling other administrative endpoints on the Minas Gerais (Estado) portal.

Your agent runs `get_resource` via the Google ADK to locate the file URL, then uses Google Cloud client libraries to load that file into BigQuery. The agent automates the transfer, letting you query the state's public data alongside your internal datasets.

Yes, it supports both transport methods. Setting up connection parameters depends on whether you run the server locally or host it on Vinkius.

The server only accesses public datasets and administrative metadata from the state's open portal. Vinkius runs the server in an isolated sandbox, ensuring your Google ADK queries and API tokens never persist on external disks.

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