How to Use the Mato Grosso do Sul Open Data MCP in Pydantic AI

Q: How do I connect Pydantic AI to the Mato Grosso do Sul Open Data MCP Server?

Run pip install "pydantic-ai-slimmcp" and initialize the unified MCPToolset with the Vinkius HTTP URL. Pass this toolset into the toolsets list when defining your Pydantic AI Agent.

Q: How does Pydantic AI validate SQL results from Mato Grosso do Sul Open Data?

When the agent calls datastoresearchsql, the returned CKAN datastore records are validated against your Pydantic models at runtime. If a column contains unexpected nulls or wrong types, the agent raises a validation error immediately.

Q: Can I use SSE transport to query Mato Grosso do Sul Open Data in Pydantic AI?

Yes, the unified MCPToolset supports both Streamable HTTP and SSE transports. This allows your agent to query getpackage and listpackages over a persistent, secure connection managed by Vinkius.

Query Mato Grosso do Sul Open Data with Pydantic AI and this MCP Server to ensure every public SQL record is strictly validated.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mato Grosso do Sul Open Data MCP to Pydantic AI

Create your Vinkius account to connect Mato Grosso do Sul Open Data 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 Mato Grosso do Sul Open Data with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe SQL Querying with Pydantic AI

The `datastore_search_sql` tool executes SQL queries against the Mato Grosso do Sul datastores while enforcing strict type safety on the returned rows. If the CKAN API returns malformed data, your Pydantic AI agent catches the schema mismatch instantly. You set this up by passing `MCPToolset` with your Vinkius server URL to the `toolsets` argument of your `Agent`. This ensures that every public record pulled via `datastore_search` matches your expected Python types before your application processes them.

Fail-Safe Dataset and Package Discovery

The `list_packages` and `get_package` tools allow your agent to discover available datasets without risking silent data corruption. Because Pydantic AI validates every field at runtime, your agent won't hallucinate missing metadata fields. This MCP Server runs externally, and your agent connects using the unified `MCPToolset` class over Streamable HTTP or SSE. The agent can safely query `list_groups` and `list_organizations` to build a type-safe map of the state's public data portals.

Strict Resource Inspection and Data Validation

The `get_resource` and `datastore_search` tools retrieve specific data slices from public tables. Pydantic AI ensures that any null values or unexpected data types in the public CSV files are flagged immediately during validation. By avoiding the deprecated HTTP classes and using the unified toolset setup, your agent maintains a stable connection to the state's CKAN API. The agent can safely cross-reference results from `list_packages` and verify data integrity before saving it.

Setup guide

Set up Mato Grosso do Sul Open Data 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": {
        "mato-grosso-do-sul-open-data-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Mato Grosso do Sul Open Data tools.",
)

result = await agent.run("List recent Mato Grosso do Sul Open Data 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 Mato Grosso do Sul 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 Mato Grosso do Sul Open Data 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 Mato Grosso do Sul Open Data MCP in Pydantic AI

Run `pip install "pydantic-ai-slim[mcp]"` and initialize the unified `MCPToolset` with the Vinkius HTTP URL. Pass this toolset into the `toolsets` list when defining your Pydantic AI `Agent`.

When the agent calls `datastore_search_sql`, the returned CKAN datastore records are validated against your Pydantic models at runtime. If a column contains unexpected nulls or wrong types, the agent raises a validation error immediately.

Yes, the unified `MCPToolset` supports both Streamable HTTP and SSE transports. This allows your agent to query `get_package` and `list_packages` over a persistent, secure connection managed by Vinkius.

The unified toolset simplifies your codebase and ensures long-term compatibility when querying tools like `list_organizations` or `get_resource`. It automatically handles the underlying transport protocol without extra boilerplate.

All API requests for Brazilian state public records run inside isolated V8 sandboxes that discard runtime data immediately after execution. Your custom validation schemas and API keys remain strictly local and are never stored on the host.

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