How to Use the Datos Abiertos Castilla-La Mancha MCP in LlamaIndex

Q: How do I prevent hallucinations when querying Datos Abiertos Castilla-La Mancha with LlamaIndex?

You force the LlamaIndex agent to use the searchdatastore tool to fetch raw numbers. This grounds the response in actual Castilla-La Mancha data rather than relying on the model's weights.

Q: Can I build a vector index of the Datos Abiertos Castilla-La Mancha catalog?

Yes, you can use listdatasets to pull the entire catalog description into LlamaIndex. From there, you chunk and embed the dataset metadata for fast semantic search.

Index Castilla-La Mancha public datasets into your LlamaIndex vector store for grounded RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Datos Abiertos Castilla-La Mancha MCP to LlamaIndex

Create your Vinkius account to connect Datos Abiertos Castilla-La Mancha 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 Datos Abiertos Castilla-La Mancha with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Spanish public data into LlamaIndex

This MCP Server exposes `list_datasets` and `get_dataset` to let your LlamaIndex pipelines ingest Spanish regional data. Your pipeline queries the portal, fetches the metadata, and indexes it directly. This keeps your local knowledge base updated with live government records. Instead of relying on static files, your RAG application queries the live API. Your agent gets the latest regional figures without manual downloads.

Query datastores directly through LlamaIndex tools

The `search_datastore` tool allows LlamaIndex agents to run targeted queries on tabular regional data. Your agent extracts specific rows from Castilla-La Mancha databases. It converts these raw database rows into searchable document nodes on the fly. You can configure the indexer to run this tool on a schedule. This ensures your semantic search results stay grounded in actual, current Spanish public records.

Extract resource metadata using `get_resource`

The `get_resource` tool retrieves the exact file download URLs and formats from the Castilla-La Mancha portal through our MCP connection. LlamaIndex uses this metadata to decide whether to download a CSV or parse a PDF. Your pipeline avoids ingestion errors by checking the resource format first. Combining this tool with `list_tags` allows your agent to build a map of available public resources. It structures the unstructured regional catalog before indexing.

Setup guide

Set up Datos Abiertos Castilla-La Mancha 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 Datos Abiertos Castilla-La Mancha 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 Datos Abiertos Castilla-La Mancha tools.",
)
response = await agent.run("List recent Datos Abiertos Castilla-La Mancha 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 Datos Abiertos Castilla-La Mancha. 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 Datos Abiertos Castilla-La Mancha 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 Datos Abiertos Castilla-La Mancha MCP in LlamaIndex

You force the LlamaIndex agent to use the `search_datastore` tool to fetch raw numbers. This grounds the response in actual Castilla-La Mancha data rather than relying on the model's weights.

Yes, you can use `list_datasets` to pull the entire catalog description into LlamaIndex. From there, you chunk and embed the dataset metadata for fast semantic search.

The MCP tools return the original Spanish text from the portal. Your LlamaIndex LLM handles the translation or queries the index directly using Spanish embeddings.

No, the portal is public, and Vinkius manages the connection details. Your LlamaIndex client only needs your single Vinkius endpoint token to start querying.

The data flows through an isolated, zero-trust sandbox directly to your local LlamaIndex pipeline. Vinkius never caches the actual content of the regional datasets or your search queries.

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