How to Use the Acre Dados Abertos MCP in Pydantic AI

Q: Can I use Pydantic AI to search for specific data inside a file from Acre Dados Abertos?

Yes, you'd use the searchdatastore tool. Pydantic AI will pass your query to the server, and the structured JSON response will be validated before it's handed back to your agent. You get type-safe search results.

Q: What happens if the Acre Dados Abertos API changes unexpectedly when I'm using Pydantic AI?

Your agent will raise a ValidationError. Pydantic AI's core feature is to fail loudly and immediately if the data structure deviates from what you've defined. This protects your system from unpredictable API changes.

Query Brazilian public data with guaranteed type-safety. Get structured, validated responses from Acre's open data using 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 Acre Dados Abertos MCP to Pydantic AI

Create your Vinkius account to connect Acre Dados Abertos 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 Acre Dados Abertos with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Data Search

Use `search_packages` to find datasets and `search_datastore` to query their contents. The difference is that you're not just getting back a blob of JSON. With Pydantic AI, every response is automatically parsed and validated against a strict schema. If the Acre API ever returns an unexpected field or a wrong data type, your code will raise a `ValidationError` immediately. No silent data corruption, just reliable, structured output every time.

Explore Data Catalogs Reliably

Your agent can map out the entire data offering using tools like `list_groups`, `list_organizations`, and `list_packages`. These tools give you the raw materials to build a complete picture of what's available. Because you're using Pydantic AI, you can define Pydantic models for what a 'Group' or 'Organization' should look like. The framework ensures that the data your agent gets from this MCP Server always matches your definitions. It's a simple way to build robust, predictable data-gathering agents.

Get Validated Metadata Models

When you need the specifics, your agent will use `get_package` or `get_resource`. This is where you get the deep metadata—licensing, file types, descriptions, update dates. This isn't just a dictionary; Pydantic AI turns that response into a clean, typed object. You get IDE autocompletion and static analysis for free. If the API changes unexpectedly, you'll know at runtime, not when your downstream logic breaks.

Setup guide

Set up Acre Dados Abertos 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": {
        "acre-dados-abertos-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Acre Dados Abertos 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 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 Pydantic AI

Pydantic AI automatically validates every API response from the MCP Server against a Pydantic model. If the data doesn't match the expected structure—for example, a string where a number should be—it raises an error. This prevents corrupted or unexpected data from entering your application.

Yes, you'd use the `search_datastore` tool. Pydantic AI will pass your query to the server, and the structured JSON response will be validated before it's handed back to your agent. You get type-safe search results.

Your agent will raise a `ValidationError`. Pydantic AI's core feature is to fail loudly and immediately if the data structure deviates from what you've defined. This protects your system from unpredictable API changes.

It works with anything Pydantic AI supports. Because this is a standard MCP Server, you can plug it into an agent running on OpenAI, Anthropic, Gemini, or a local model you're running yourself. The tool interaction is model-agnostic.

The server's scope is strictly limited to the public data published by the Acre government; it doesn't handle any personal data. Vinkius provides an authentication layer, so your API keys are never shared with the server. All requests are processed in a dedicated, single-use environment that is destroyed after your query is complete.

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