How to Use the Minas Gerais (Estado) MCP in Pydantic AI

Q: How do I register the Minas Gerais (Estado) MCP Server tools in pydantic-ai?

Use the MCPToolset class with the server's HTTP URL and pass it to your agent's toolsets parameter. Pydantic AI auto-discovers all ten tools, including listpackages and getpackage, validating their schemas at runtime.

Q: What happens if the Minas Gerais (Estado) portal changes its API schema under pydantic-ai?

If the state portal returns unexpected fields during a getresource call, Pydantic AI raises a validation error. This prevents your agent from hallucinating properties or working with corrupted data structures.

Q: Can I use pydantic-ai to search Minas Gerais (Estado) tags safely?

Yes, the listtags tool returns a structured list that Pydantic AI validates against its internal models. To filter datasets safely, your agent uses these verified tags without risk of type mismatches.

Query the Minas Gerais (Estado) MCP Server with strict runtime validation using the Pydantic AI framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Minas Gerais (Estado) MCP to Pydantic AI

Create your Vinkius account to connect Minas Gerais (Estado) 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 Minas Gerais (Estado) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate State Metadata at Runtime

`get_package` and `get_resource` return public data from the Minas Gerais (Estado) portal over an MCP link that Pydantic AI validates against strict schemas instantly. If the state API returns unexpected nulls or modified fields, the framework raises a validation error immediately. This strict type checking prevents silent data corruption in your data pipelines. You catch schema drift on the Brazilian state's portal before it breaks downstream analytical models.

Type-Safe Search on Minas Gerais (Estado) MCP Server

This MCP Server integrates with Pydantic AI to enforce type safety on search parameters and responses. When your agent calls `search_packages` or `search_resources`, the input arguments are validated before they reach the network. The returned list of public datasets is parsed into structured Python objects, ensuring your agent never processes malformed JSON. Adding these validations makes your data collection scripts highly resilient.

Structured Navigation of State Organizations

`list_organizations` and `list_groups` output structured lists of Minas Gerais (Estado) administrative bodies. Pydantic AI verifies that every organization object contains the expected identifier and package count. Your agent uses this verified structure to safely traverse the state's organizational tree. By declaring schemas upfront, you write clean, typed Python code that handles government data without messy manual parsing.

Setup guide

Set up Minas Gerais (Estado) 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": {
        "minas-gerais-estado-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Minas Gerais (Estado) 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 Minas Gerais Open Data. 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 Minas Gerais (Estado) 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 Minas Gerais (Estado) MCP in Pydantic AI

Use the `MCPToolset` class with the server's HTTP URL and pass it to your agent's `toolsets` parameter. Pydantic AI auto-discovers all ten tools, including `list_packages` and `get_package`, validating their schemas at runtime.

If the state portal returns unexpected fields during a `get_resource` call, Pydantic AI raises a validation error. This prevents your agent from hallucinating properties or working with corrupted data structures.

Yes, the `list_tags` tool returns a structured list that Pydantic AI validates against its internal models. To filter datasets safely, your agent uses these verified tags without risk of type mismatches.

It supports both Streamable HTTP and SSE transports. You configure your Pydantic AI toolset to connect to the external Vinkius-hosted server endpoint using your preferred protocol.

The server only processes public administrative metadata and resource schemas. Vinkius enforces a zero-trust model where your Pydantic AI queries run in ephemeral, isolated sandboxes that destroy all session state upon disconnection.

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