How to Use the Ayuntamiento de Zaragoza MCP in Pydantic AI

Q: How do I configure the Ayuntamiento de Zaragoza MCP Server in Pydantic AI?

Install pydantic-ai-slimmcp and initialize MCPToolset pointing to the Vinkius server URL. Pass this toolset directly to your Agent's toolsets parameter to instantly expose all 17 municipal tools.

Q: How do I handle authenticated Ayuntamiento de Zaragoza tools in Pydantic AI?

For tools like createmap or deletemap that require authentication, you pass the credentials through the agent's run context. The framework injects these headers into the tool calls dynamically during runtime execution.

Q: How does this MCP Server protect Zaragoza mapping and citizen data?

All coordinate data from getmapdetail and citizen inputs are processed in Vinkius's isolated V8 sandboxes. No municipal datasets or user credentials are stored permanently or leaked to external LLM providers.

Run type-safe queries against this Zaragoza MCP Server with Pydantic AI validating every single tool response.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ayuntamiento de Zaragoza MCP to Pydantic AI

Create your Vinkius account to connect Ayuntamiento de Zaragoza 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 Ayuntamiento de Zaragoza with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe citizen reporting with Pydantic AI

The `submit_open311_request` tool posts citizen complaints directly to Zaragoza's public tracking system. Pydantic AI ensures that every field in the request matches the strict municipal API schema before firing the payload. When reading issues via `get_open311_request`, the framework validates the response against your typed models. If the Zaragoza API returns an unexpected data type, the agent fails immediately instead of processing corrupted data.

Validated appointment scheduling

The `book_appointment` tool schedules real-world appointments with Zaragoza city offices. Pydantic AI validates the date and time strings returned by `get_agenda_availability` to ensure they conform to ISO formats. Your agent can list active bookings with `get_my_appointments` or inspect specific office hours using `get_agenda_detail`. Every piece of scheduling data is cast into typed Python models before your agent can act on it.

Structured semantic querying

The `execute_sparql_query` tool queries Zaragoza's RDF database via this MCP Server to retrieve structured city information. Pydantic AI parses the SPARQL response format, ensuring the agent receives clean, predictable objects. If you are pulling general datasets using `query_dataset`, the framework validates attributes like coordinates or phone numbers. This prevents your agent from hallucinating properties that do not exist in the municipal registry.

Setup guide

Set up Ayuntamiento de Zaragoza 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": {
        "ayuntamiento-de-zaragoza-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Ayuntamiento de Zaragoza 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 Ayuntamiento de Zaragoza. 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 Ayuntamiento de Zaragoza 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 Ayuntamiento de Zaragoza MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` and initialize `MCPToolset` pointing to the Vinkius server URL. Pass this toolset directly to your Agent's `toolsets` parameter to instantly expose all 17 municipal tools.

Yes, the framework validates all incoming data from tools like `get_open311_service` against runtime Pydantic models. If the Zaragoza API changes its payload structure, your agent catches the validation error instantly.

For tools like `create_map` or `delete_map` that require authentication, you pass the credentials through the agent's run context. The framework injects these headers into the tool calls dynamically during runtime execution.

Yes, Pydantic AI is completely model-agnostic. You can run the Zaragoza tools using local models via Ollama or commercial models from Anthropic and OpenAI without changing your tool configuration.

All coordinate data from `get_map_detail` and citizen inputs are processed in Vinkius's isolated V8 sandboxes. No municipal datasets or user credentials are stored permanently or leaked to external LLM providers.

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