How to Use the ANA (Movimentação de Dados) MCP in Pydantic AI

Run type-safe water data operations using the ANA (Movimentação de Dados) MCP Server in Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect ANA (Movimentação de Dados) to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate water data writes with Pydantic AI

`create_serie_qa` allows your agent to submit new water quality measurements with strict runtime type validation. If the model attempts to pass an invalid pH value or malformed date, Pydantic AI rejects it instantly before it ever reaches the ANA server. This strictness prevents silent data corruption in your hydrometeorological databases. You can rest assured that operations like `create_serie_resumo_descarga` only execute when the data strictly matches your Pydantic schemas.

Query river metrics using a type-safe MCP Server

`get_serie_cota` fetches river stage levels, ensuring that every float, timestamp, and station ID is parsed into a strictly typed Python object. If the API schema changes unexpectedly, your agent fails loudly and immediately, rather than hallucinating missing metrics. This model-agnostic framework works perfectly with this MCP Server. Whether you are using Anthropic, OpenAI, or a local model, the data returned by `get_serie_perfil_transversal` is validated at the edge.

Update flow records securely with Pydantic AI

`update_serie_vazao` modifies river flow records, requiring the agent to provide perfectly formatted inputs. If the model tries to guess a field name, the validation layer throws an error, forcing the agent to self-correct or stop. This makes it highly reliable for managing environmental records. By using `update_serie_chuva` within a type-safe pipeline, you eliminate the risk of corrupting critical historical rainfall data.

Setup guide

Set up ANA (Movimentação de Dados) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "ana-movimentacao-de-dados-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to ANA (Movimentação de Dados) tools.",
)

result = await agent.run("List recent ANA (Movimentação de Dados) transactions")
print(result.output)

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 Pydantic AI

Every response from the MCP Server is validated against strict Pydantic models at runtime. If the water agency API returns unexpected types, the framework raises a validation error immediately.

Yes, Pydantic AI is model-agnostic. You can connect this server to local models or commercial APIs while maintaining the exact same type-safety for tools like get_serie_chuva.

You initialize the MCPToolset with the Vinkius HTTP endpoint and pass it to your Agent's toolsets list. The setup handles the SSE transport securely under the hood.

The validation layer will catch the invalid schema and throw a runtime error. The agent will either receive the validation error to self-correct or halt execution, preventing corrupt data writes.

All data passing through the Vinkius-hosted server is isolated in a zero-trust sandbox. The strict validation in your local Python environment ensures no malformed or leaky data ever reaches the Brazilian National Water Agency endpoints.

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