How to Use the IBGE Agregados (SIDRA) MCP in Google ADK

Q: How do I configure Google ADK to run IBGE Agregados (SIDRA) tools?

Just run pip install google-adk and pass your Vinkius HTTP URL into McpToolset. Register that MCP toolset in your LlmAgent call. That covers it.

Q: Can I restrict which IBGE Agregados (SIDRA) tools are exposed to Google ADK?

Yes, you can use the toolnames filter in your toolset setup to limit access. For example, you can expose only getvariaveis and block discovery tools like listagregados.

Q: How does Google ADK handle large metadata payloads from IBGE Agregados (SIDRA)?

The getmetadados tool can return large structures, but Gemini's long-context window handles them easily. The agent processes the complete table metadata without needing aggressive truncation or filtering.

Q: Can I combine these statistical tools with BigQuery workflows?

Yes, you can write agents that fetch metadata via getlocalidades and then trigger BigQuery jobs to join those regions with your internal tables. This connects official Brazilian statistics with your private data warehouse.

Feed official IBGE Agregados (SIDRA) data directly into your Gemini long-context models using Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IBGE Agregados (SIDRA) MCP to Google ADK

Create your Vinkius account to connect IBGE Agregados (SIDRA) 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 IBGE Agregados (SIDRA) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Scan the SIDRA index with `list_agregados`

The `list_agregados` tool searches the complete list of IBGE statistical tables directly from your enterprise pipeline. Your Gemini agent uses it to locate specific economic indicators and demographic surveys via the MCP server. Because Google ADK supports massive context windows, your agent can process this entire directory in a single turn. This lets the model evaluate multiple tables side-by-side to find the exact dataset needed.

Map regional data using `get_localidades`

The `get_localidades` tool extracts the geographic divisions available for any statistical aggregate. Your agent queries this endpoint to map municipalities, metropolitan areas, or states. Connecting this MCP server to BigQuery is handled directly by the Google ADK toolset. This makes it simple to join official Brazilian census boundaries with your internal enterprise data.

Inspect schemas with this Google ADK MCP Server

The `get_metadados` tool retrieves structural metadata, while `get_variaveis` and `get_periodos` pull the specific variables and timeframes. Your agent calls these tools to understand the shape of the table before executing deep reasoning tasks. This structural lookup runs before any data analysis step. It ensures your Gemini model relies on verified schemas rather than guessing the variable codes or temporal limits of the IBGE database.

Setup guide

Set up IBGE Agregados (SIDRA) 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 IBGE Agregados (SIDRA) 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="IBGE Agregados (SIDRA)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to IBGE Agregados (SIDRA) 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 IBGE Agregados (SIDRA). 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 IBGE Agregados (SIDRA) 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 IBGE Agregados (SIDRA) MCP in Google ADK

Just run `pip install google-adk` and pass your Vinkius HTTP URL into `McpToolset`. Register that MCP toolset in your `LlmAgent` call. That covers it.

Yes, you can use the `tool_names` filter in your toolset setup to limit access. For example, you can expose only `get_variaveis` and block discovery tools like `list_agregados`.

The `get_metadados` tool can return large structures, but Gemini's long-context window handles them easily. The agent processes the complete table metadata without needing aggressive truncation or filtering.

Yes, you can write agents that fetch metadata via `get_localidades` and then trigger BigQuery jobs to join those regions with your internal tables. This connects official Brazilian statistics with your private data warehouse.

Your queries for Brazilian demographic and economic metrics pass through a zero-trust V8 sandbox. Vinkius secures the endpoint with a single token, and no data is persisted outside your Google Cloud environment.

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