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

Q: How can my LangChain agent find all CSV datasets about finance from Datos.gob.es (Catálogo Nacional)?

Your agent would chain two tool calls. First, it would use listdatasetsbytheme with 'hacienda' to get finance-related datasets. Then, it would pass those results to listdatasetsbyformat with 'csv' to filter for the correct file type.

Q: What's the best way to handle multiple datasets from Datos.gob.es (Catálogo Nacional) in a single LangChain chain?

Use a map-reduce approach. Have your agent call listdatasets to get a list, then create a parallel chain that runs getdataset for each item. Finally, a concluding chain can synthesize the results from all the parallel runs.

Q: Can I get a list of all data publishers?

Yes, just have your agent call the listpublishers tool. It returns a complete list of all publishers available in the catalog.

Build LangChain agents that search Spain's open data catalog, linking one discovery to the next.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Data Discovery Steps

This isn't about one-off queries. It's about building a logical path through data. Start with a broad search using `list_themes`. Pipe that theme into `list_datasets_by_theme`. Then, grab a dataset ID from the results and pull its specific details with `get_dataset`. LangChain makes this sequential logic work. Your agent isn't just calling a tool; it's following a trail of breadcrumbs through the catalog. It's how you go from a vague idea like "I need data about finance" to a specific dataset file. This MCP server provides the breadcrumbs.

Build Dynamic Data Filters with LangChain

Your ReAct agent can decide which filter to apply based on what it learns. It might start with `search_datasets_by_title`, find nothing useful, and then pivot to `list_datasets_by_keyword` on its own. It's an agent using the tools to adapt its search strategy on the fly. This isn't a pre-programmed script. You give the agent a goal and a set of tools from this MCP Server. The agent figures out the path, chaining calls to `list_datasets_by_publisher` or `list_datasets_by_format` until it finds what you asked for.

Combine Public Data with Your Own

Pull a list of provinces from Spain's national catalog using the `list_provinces` tool. That's the first step. The second step is using another LangChain integration to cross-reference that list with your company's database of office locations or sales territories. This is where it gets powerful. This MCP connection gives you the public data half of the equation. LangChain is what lets you connect it to all the private data and other APIs you already use.

Setup guide

Set up Datos.gob.es (Catálogo Nacional) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Datos.gob.es (Catálogo Nacional) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "datosgobes-catalogo-nacional-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Datos.gob.es (Catálogo Nacional) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Your agent would chain two tool calls. First, it would use `list_datasets_by_theme` with 'hacienda' to get finance-related datasets. Then, it would pass those results to `list_datasets_by_format` with 'csv' to filter for the correct file type.

Yes. LangChain's observability tools like LangSmith work out of the box. You'll see every call to this MCP server, including the exact inputs to tools like `get_dataset` and the data that comes back.

Use a map-reduce approach. Have your agent call `list_datasets` to get a list, then create a parallel chain that runs `get_dataset` for each item. Finally, a concluding chain can synthesize the results from all the parallel runs.

Yes, just have your agent call the `list_publishers` tool. It returns a complete list of all publishers available in the catalog.

You're only touching public data. This server handles public catalog metadata like dataset titles, publisher IDs, and distribution formats. Vinkius runs your connection in an ephemeral sandbox, ensuring your session is isolated and destroyed after use. Nothing about your query persists on the server.

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