How to Use the Datos.gob.es (Catálogo Nacional) MCP in LlamaIndex

Q: How do I create a LlamaIndex index from datasets by publisher 'A16003011' in Datos.gob.es (Catálogo Nacional)?

It's a two-step process. First, use the listdatasetsbypublisher tool with the ID 'A16003011'. Then, iterate through the returned dataset list, calling getdataset on each one and passing the output to your LlamaIndex indexer.

Q: Can I use LlamaIndex to query my Datos.gob.es (Catálogo Nacional) search history?

Yes, indirectly. LlamaIndex excels at indexing the results of your searches. Every time your agent uses this MCP server to pull data, you can have LlamaIndex add that data to its knowledge base, making your past findings searchable.

Q: How do I find all the geographic options for filtering?

Simple. Call the listspatialoptions tool. It gives you a list of all the valid geographic coverage terms you can use for filtering datasets.

Turn Spain's open data into a queryable knowledge base for your LlamaIndex 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.gob.es (Catálogo Nacional) MCP to LlamaIndex

Create your Vinkius account to connect Datos.gob.es (Catálogo Nacional) 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.gob.es (Catálogo Nacional) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Public Data for RAG

Don't just fetch data, index it. Use the `list_datasets_by_theme` and `get_dataset` tools to pull information on a topic like 'hacienda' (finance). LlamaIndex will automatically process the text and metadata from these tool calls and feed it into a vector store. Suddenly you have a private, searchable index of Spanish public finance data. When you ask a question, your app queries your index, not the live API every single time. It's faster and gives you more control.

Answer Questions with Indexed Facts

Once your index is built, you can ask plain-English questions. "What datasets are available from the Madrid region?" Your LlamaIndex agent won't guess or hallucinate. It will perform a semantic search over the data it already indexed from the `list_datasets_by_spatial` and `get_region` tools. This grounds your agent's answers in actual data from the catalog. The MCP server provides the raw material, and LlamaIndex turns it into a verifiable knowledge source.

Keep Your LlamaIndex Knowledge Base Fresh

This isn't a one-time data dump. You can set up a routine that calls `list_datasets_by_date` to find only the datasets modified in the last week. Then you feed just those updates into your LlamaIndex vector store. This way, your RAG application always has the latest information from the Datos.gob.es catalog without doing a full, costly re-index. This MCP Server gives you the specific tools you need for these targeted updates.

Setup guide

Set up Datos.gob.es (Catálogo Nacional) 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.gob.es (Catálogo Nacional) 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.gob.es (Catálogo Nacional) tools.",
)
response = await agent.run("List recent Datos.gob.es (Catálogo Nacional) 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.gob.es. 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.gob.es (Catálogo Nacional) 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.gob.es (Catálogo Nacional) MCP in LlamaIndex

It's a two-step process. First, use the `list_datasets_by_publisher` tool with the ID 'A16003011'. Then, iterate through the returned dataset list, calling `get_dataset` on each one and passing the output to your LlamaIndex indexer.

Yes, indirectly. LlamaIndex excels at indexing the *results* of your searches. Every time your agent uses this MCP server to pull data, you can have LlamaIndex add that data to its knowledge base, making your past findings searchable.

That's exactly what LlamaIndex is for. Ingest your private documents into a vector index. Then, use the tools on this server to pull public data and ingest it into the same index. LlamaIndex unifies them, letting you query across both sources at once.

Simple. Call the `list_spatial_options` tool. It gives you a list of all the valid geographic coverage terms you can use for filtering datasets.

Your queries are safe. The server only processes requests for public catalog information—dataset themes, formats, and spatial coverage options. Your process runs in a V8 isolate sandbox on Vinkius, which means it's completely walled off from others. The connection is encrypted, and your token is the only credential.

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