How to Use the Ayuntamiento de Zaragoza MCP in LlamaIndex

Q: Can I filter which Ayuntamiento de Zaragoza tools my LlamaIndex agent sees?

Yes. Use the allowedtools parameter in your tool spec. You might restrict a public bot to just querydataset and listpublicmaps to prevent unauthorized actions.

Q: Will LlamaIndex cache Ayuntamiento de Zaragoza appointment slots?

The framework indexes the output of getagendaavailability at the moment of execution. You configure the refresh interval to drop stale embeddings and pull fresh availability data.

Feed LlamaIndex with live Zaragoza city data to build RAG applications that answer questions using real municipal records.

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 LlamaIndex

Create your Vinkius account to connect Ayuntamiento de Zaragoza to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Zaragoza MCP Server datasets

LlamaIndex treats municipal data as dynamic context for your vector store. You pull restaurant and monument lists using `query_dataset` and embed the results directly into your index. When users ask about local attractions, the engine searches this live knowledge base instead of relying on stale training data. Semantic web queries add another layer of depth to your RAG pipeline. The agent executes complex searches via `execute_sparql_query` and merges the returned RDF triples with your existing document embeddings. You get answers grounded in the city's official semantic endpoint.

Search public collaborative maps

Spatial data becomes searchable text when you feed map details into your index. The system calls `list_public_maps` and iterates through the results with `get_map_detail` to extract point-of-interest descriptions. Your users query the vector store to find community-curated routes or historical markers. Authenticated users can manage their own spatial data through the same interface. The agent uses `list_user_maps` to index private maps, then allows natural language querying against those specific boundaries. You build localized search engines in minutes.

Ground 311 requests in history

Citizen support bots need context before logging new complaints. Your application indexes historical issues using `list_open311_requests` so the agent knows if a broken streetlight was already reported. It verifies the correct department by checking `get_open311_service` against the vector store. Submitting new tickets happens through the same MCP tool specification. After confirming the issue is unique, the agent calls `submit_open311_request` to log the complaint. The output immediately updates your local index, keeping the RAG application perfectly synchronized with city systems.

Setup guide

Set up Ayuntamiento de Zaragoza MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Ayuntamiento de Zaragoza MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Ayuntamiento de Zaragoza tools.",
)
response = await agent.run("List recent Ayuntamiento de Zaragoza data")

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 LlamaIndex

Initialize a BasicMCPClient with your Vinkius URL. Pass it to McpToolSpec and call to_tool_list_async() to expose the city tools to your FunctionAgent.

Yes. Use the allowed_tools parameter in your tool spec. You might restrict a public bot to just `query_dataset` and `list_public_maps` to prevent unauthorized actions.

The framework indexes the output of `get_agenda_availability` at the moment of execution. You configure the refresh interval to drop stale embeddings and pull fresh availability data.

The Vinkius endpoint handles the actual integration authentication. You supply your single access token when setting up the HTTP transport for tools like `create_map`.

The zero-trust architecture ensures data isolation. When your MCP connection calls `get_map_detail`, the geographic coordinates and user notes stay within your specific LlamaIndex memory structure and never bleed into other tenants.

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