4,500+ servers built on MCP Fusion
Vinkius
Maranhão Open Data logo
Vinkius
Pydantic AI logo

How to Use the Maranhão Open Data MCP in Pydantic AI

Type-safe access to Maranhão Open Data for Pydantic AI. Enforce strict validation on Brazilian public records before your agent acts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Maranhão Open Data MCP on Cursor AI Code Editor MCP Client Maranhão Open Data MCP on Claude Desktop App MCP Integration Maranhão Open Data MCP on OpenAI Agents SDK MCP Compatible Maranhão Open Data MCP on Visual Studio Code MCP Extension Client Maranhão Open Data MCP on GitHub Copilot AI Agent MCP Integration Maranhão Open Data MCP on Google Gemini AI MCP Integration Maranhão Open Data MCP on Lovable AI Development MCP Client Maranhão Open Data MCP on Mistral AI Agents MCP Compatible Maranhão Open Data MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Pydantic AI

Connect Maranhão Open Data MCP to Pydantic AI

Create your Vinkius account to connect Maranhão 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

Type-safe dataset discovery

Government APIs are notorious for returning inconsistent JSON. Pydantic AI fixes this by validating every MCP response. When your agent calls `search_packages`, the framework ensures the returned dataset list matches your expected schema. When the Maranhão portal randomly changes its response format for `list_packages`, your agent fails loudly with a validation error. You get a stack trace immediately. No silent failures. No hallucinated fields making it into your production database.

Query the Maranhão Open Data MCP Server

You want exact answers from public records, not summaries. Your agent uses `search_datastore_sql` to execute raw SQL queries against the portal's datastore. It gets exactly the rows it asks for. For basic lookups, it drops back to `search_datastore`. Because Pydantic AI is model-agnostic, you can swap between Anthropic for writing complex SQL and a cheaper local model for basic key-value searches. The tool execution remains identical.

Validate resource endpoints strictly

Your agent needs to verify what a dataset actually contains before attempting to parse it. It runs `get_package` for the broad metadata, then uses `get_resource` to pinpoint the exact file types. It checks if the resource is a valid CSV or a broken link. By validating this metadata through Pydantic models at runtime, your system guarantees it never passes a malformed URL to your downstream ingestion scripts.

Setup guide

Set up Maranhão 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. 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. 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. 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": {
        "maranhao-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 Maranhão Open Data tools.",
)

result = await agent.run("List recent Maranhão Open Data transactions")
print(result.output)

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Maranhão 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.

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 Maranhão Open Data MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]`. Initialize an `MCPToolset` with your Vinkius HTTP URL. Pass this toolset directly to your Agent. Do not use the deprecated `MCPServerHTTP` class.
Pydantic AI validates the inputs going into `search_datastore_sql` and the schema of the response coming back. It does not parse the SQL syntax itself, but it ensures the agent's tool call matches the required parameters.
The framework throws a strict validation error. If the Brazilian portal returns a string where an integer was expected, the agent stops execution. It refuses to process corrupted data.
Yes. Since the framework is model-agnostic, you can connect a local Llama model to search packages or list resources, saving API costs on simpler discovery tasks.
You are querying public Brazilian state datasets. The primary security feature here is data integrity. Pydantic AI guarantees that the public records you pull match your schemas, preventing injection of malformed data into your local systems.

Start using the Maranhão Open Data MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 6 tools

We've already built the connector for Maranhão Open Data. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 6 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.