How to Use the Comunidad de Madrid (Portal Regional) MCP in Pydantic AI

Q: How do I connect the Comunidad de Madrid (Portal Regional) MCP Server to Pydantic AI?

Install the package using pip install "pydantic-ai-slimmcp". Use MCPToolset with your Vinkius HTTP endpoint, and pass it to your Agent constructor in the toolsets list.

Q: Is the deprecated MCPServerHTTP class needed for this server?

No, you should use the unified MCPToolset class instead. The older MCPServerHTTP transport class is deprecated and should not be used in your new codebases.

Query Comunidad de Madrid open data with strict, type-safe runtime validation 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 Comunidad de Madrid (Portal Regional) MCP to Pydantic AI

Create your Vinkius account to connect Comunidad de Madrid (Portal Regional) 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 Comunidad de Madrid (Portal Regional) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Madrid Data Queries with Pydantic AI

`search_datastore` executes queries against Madrid's database and validates the returned JSON against your strict Pydantic models. If the portal changes its schema, your agent catches the error instantly so you don't process corrupted data. This MCP Server ensures that every row returned from the regional datastore matches the exact type definitions your Python application expects. This guarantees type safety across your entire data ingestion pipeline.

Type-Checked Catalog Exploration

`search_datasets` and `list_datasets` return validated lists of public datasets from the Madrid regional portal. Pydantic AI parses these lists into structured Python objects, making it impossible for your agent to hallucinate non-existent dataset IDs. Your agent can safely iterate over these validated datasets to find specific public records. The framework enforces strict type checking on every metadata field returned by the portal.

Verified Resource Metadata Extraction

`get_resource` and `get_dataset` fetch the exact structural metadata for any public resource in the Madrid portal. Your agent inspects these fields to determine the resource's format and update its query parameters. Because Pydantic AI is model-agnostic, you can use these validated MCP Server tools with any LLM. The runtime validation acts as an independent firewall, protecting your application from unexpected API changes on the Madrid portal.

Setup guide

Set up Comunidad de Madrid (Portal Regional) 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": {
        "comunidad-de-madrid-portal-regional-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Comunidad de Madrid (Portal Regional) tools.",
)

result = await agent.run("List recent Comunidad de Madrid (Portal Regional) 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 Comunidad de Madrid (Portal Regional). 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 Comunidad de Madrid (Portal Regional) 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 Comunidad de Madrid (Portal Regional) MCP in Pydantic AI

Install the package using `pip install "pydantic-ai-slim[mcp]"`. Use `MCPToolset` with your Vinkius HTTP endpoint, and pass it to your `Agent` constructor in the `toolsets` list.

The framework raises a validation error immediately at runtime. This prevents your agent from making decisions based on malformed or incomplete regional records.

Yes, Pydantic AI is model-agnostic. You can run this server alongside local models or commercial APIs while maintaining strict type safety for all Madrid portal tools.

No, you should use the unified `MCPToolset` class instead. The older `MCPServerHTTP` transport class is deprecated and should not be used in your new codebases.

This MCP Server only queries public, non-sensitive regional datasets, so no private citizen data is processed. Pydantic AI runs these queries through Vinkius's isolated sandbox, ensuring secure, read-only access to the public records.

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