How to Use the Acre Dados Abertos MCP in Google ADK

Q: How can I use Google ADK to search for datasets in Acre Dados Abertos related to agriculture?

Your Gemini agent should use the searchpackages tool with a query like 'agricultura'. This returns a list of relevant dataset packages. It's the first step before pulling the data into your Google Cloud environment.

Q: Can my Google ADK agent find out which organization published a specific dataset from Acre Dados Abertos?

Yes. The metadata returned by getpackage includes details about the publishing organization. Your agent can also call listorganizations to get a full directory of all publishing entities to cross-reference.

Q: Is it possible to filter data within a resource from Acre Dados Abertos before downloading it with Google ADK?

Absolutely. The searchdatastore tool lets your agent run SQL-like queries against tabular data resources directly on the server. This way, you only pull the specific rows you need, saving bandwidth and processing time on your end.

Q: How do I list all thematic groups of data available?

Your agent just needs to call the listgroups tool. It returns a simple list of all categories, which you can then use to explore datasets within a specific domain like 'economics' or 'transportation'.

Connect Gemini to Brazil's public data. Build enterprise agents on Google Cloud with the Google ADK and Acre's open datasets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Acre Dados Abertos MCP to Google ADK

Create your Vinkius account to connect Acre Dados Abertos 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 Acre Dados Abertos with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Public Data for BigQuery

Your Gemini agent can use the `search_datastore` tool to pull specific records from Acre's public datasets. Think of it as a pre-filter before you bring data into your own environment. The real power is combining this with Google ADK's native tools. Have your agent find a relevant dataset ID with `search_packages`, pull the raw data with `get_resource`, and then pipe it directly into a BigQuery table for analysis alongside your private enterprise data.

Long-Context Data Discovery with Gemini

Gemini's massive context window changes how you work with this data. Your agent can call `list_packages` and `list_groups` to get a full catalog of everything available, hold it all in context, and then reason about which datasets are most relevant to a complex, multi-step query. Instead of asking 'find health data,' you can ask 'find all datasets related to dengue fever outbreaks in the last five years and cross-reference them with demographic information.' The agent can use the tools from this MCP Server to build a complete picture before it even starts downloading files.

Map Governmental Data Sources

This isn't just about the data, it's about the source. Your agent can use `list_organizations` to map out every government body publishing data through the Acre portal. Then use `get_package` to check the metadata for licensing and update frequency. For enterprise agents built with Google ADK, this is critical for compliance and data governance. You know exactly where the data came from and who published it, all before integrating it into your Google Cloud workflow.

Setup guide

Set up Acre Dados Abertos 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 Acre Dados Abertos 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="Acre Dados Abertos_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Acre Dados Abertos 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 Acre Dados Abertos. 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 Acre Dados Abertos 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 Acre Dados Abertos MCP in Google ADK

Your Gemini agent should use the `search_packages` tool with a query like 'agricultura'. This returns a list of relevant dataset packages. It's the first step before pulling the data into your Google Cloud environment.

Yes. The metadata returned by `get_package` includes details about the publishing organization. Your agent can also call `list_organizations` to get a full directory of all publishing entities to cross-reference.

Absolutely. The `search_datastore` tool lets your agent run SQL-like queries against tabular data resources directly on the server. This way, you only pull the specific rows you need, saving bandwidth and processing time on your end.

Your agent just needs to call the `list_groups` tool. It returns a simple list of all categories, which you can then use to explore datasets within a specific domain like 'economics' or 'transportation'.

The server only provides access to public datasets from the Acre government. Your agent's queries are processed, but no private information is ever stored or requested. Each connection is handled through Vinkius's zero-trust infrastructure, meaning the MCP server never sees your Google Cloud credentials, only a temporary Vinkius token.

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