How to Use the ANA (Movimentação de Dados) MCP in Google ADK

Q: Can I combine ANA (Movimentação de Dados) data with BigQuery using Google ADK?

Yes, your agent can pull data using getserieqa and immediately write those structured records into BigQuery tables for enterprise-wide analytics.

Q: Does this MCP Server support Gemini's long-context window?

Yes, you can pull massive datasets using tools like getserieperfiltransversal and feed the entire output into Gemini's 1M+ token window for deep analytical reasoning.

Q: How do I restrict write access to the water agency tools?

Use the toolnames filter in the Google ADK toolset configuration. This prevents the agent from calling write tools like updateseriechuva while keeping read tools open.

Build enterprise water data agents with the ANA (Movimentação de Dados) MCP Server and 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 ANA (Movimentação de Dados) MCP to Google ADK

Create your Vinkius account to connect ANA (Movimentação de Dados) 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 ANA (Movimentação de Dados) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process massive water datasets using Google ADK

`get_serie_vazao` retrieves extensive flow data series that Gemini can digest instantly using its million-token context window. Your Google ADK agent can ingest decades of Brazilian water flow history in a single prompt, finding trends that smaller models miss. This MCP Server connects your enterprise AI directly to the raw hydrometeorological sources. You can feed these massive outputs straight into BigQuery for further analysis, combining public water data with your internal corporate storage.

Map weather to river stages on Google Cloud

`get_serie_chuva` pulls historical rainfall data, which your agent can cross-reference with river stage levels. By invoking `get_serie_cota`, the model maps precipitation events to rising water levels across entire Brazilian basins. Because the ADK integrates natively with Vertex AI, you can easily train predictive models on this data. The agent handles the API calls, cleans up the JSON, and structures it for your enterprise data pipelines.

Monitor environmental metrics with an MCP Server

`get_serie_qa` tracks chemical and physical water quality parameters across monitored Brazilian rivers. If the agent detects an anomaly, it can use `update_serie_resumo_descarga` to update discharge summaries for compliance reporting. You can restrict which tools are exposed to the agent using the ADK's tool_names filter. This ensures your Gemini models only access the specific read or write operations required for their specific role.

Setup guide

Set up ANA (Movimentação de Dados) 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 ANA (Movimentação de Dados) 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="ANA (Movimentação de Dados)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to ANA (Movimentação de Dados) 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 ANA (Agência Nacional de Águas). 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 ANA (Movimentação de Dados) 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 ANA (Movimentação de Dados) MCP in Google ADK

You initialize the McpToolset with the Vinkius HTTP endpoint and pass it to your LlmAgent. The Gemini model can then natively call any of the 18 hydrometeorological tools.

Yes, your agent can pull data using get_serie_qa and immediately write those structured records into BigQuery tables for enterprise-wide analytics.

Yes, you can pull massive datasets using tools like get_serie_perfil_transversal and feed the entire output into Gemini's 1M+ token window for deep analytical reasoning.

Use the tool_names filter in the Google ADK toolset configuration. This prevents the agent from calling write tools like update_serie_chuva while keeping read tools open.

The MCP Server runs in an isolated V8 sandbox on Vinkius. All requests are proxied securely, and your Google Cloud credentials never touch the underlying Brazilian water agency endpoints directly.

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