Datos.gob.es Catalog MCP for AI. Find and filter public data across Spain's regions.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Datos.gob.es (Catálogo Nacional) provides access to Spain's entire repository of public sector data. Connect your AI client to search, filter, and analyze thousands of open datasets from national, regional, and local governments.
You can narrow results by theme, specific publisher, geographic area, or file format.
What your AI can do
Get country spain
Pulls general information about Spain at the national level.
Get dataset
Retrieves details for a specific dataset using its unique URI identifier.
Get province
Gets information about one specific province by ID.
Find relevant open data records across the national catalog using general search terms.
Narrow down results based on themes (e.g., education), publishers, dates, or file formats like JSON and CSV.
Limit your search to a precise area, whether it's an entire region, a specific province, or the whole country of Spain.
Get detailed information about any dataset, including its update frequency, issuing body, and available file types.
Retrieve lists of available themes, regions, provinces, or publishers to guide complex filtering queries.
Ask an AI about this
Waiting for input…
Datos.gob.es (Catálogo Nacional) with 22 Tools
These tools allow your agent to perform every necessary step of data discovery: listing available themes, filtering by specific regions, checking publishers, and getting metadata for any dataset.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Datos.gob.es (Catálogo Nacional) on VinkiusGet Country Spain
Pulls general information about Spain at the national level.
Get Dataset
Retrieves details for a specific dataset using its unique URI identifier.
Get Province
Gets information about one specific province by ID.
Get Public Sector
Retrieves data for a single primary sector using its ID.
Get Region
Gets information about a specific Autonomous Community (Region) by ID.
List Datasets By Date
Filters and lists datasets based on a specified modification date range.
List Datasets By Format
Limits the dataset list to records available in a specific file format (like CSV or JSON).
List Datasets By Keyword
Filters the entire catalog by general keywords provided by the user.
List Datasets By Publisher
Narrows down results to only those datasets published by a specific organizational...
List Datasets By Spatial
Restricts the search scope to include data tied to certain geographic areas (e.g....
List Datasets By Theme
Filters datasets by a specific category or overarching theme, like 'Health' or...
List Datasets
Retrieves a complete list of all available datasets in the national catalog.
List Distributions By Dataset
Lists the specific file format options for an already selected dataset ID.
List Distributions By Format
Filters distributions to show only those available in a certain format, like CSV.
List Distributions
Gets a list of all available data distributions and formats.
List Provinces
Pulls a complete list of all provinces within Spain.
List Public Sectors
Provides the full taxonomy and list of primary economic sectors used by publishers.
List Publishers
Retrieves a comprehensive list of every organization that has published data in the catalog.
List Regions
Gets an exhaustive list of all Autonomous Communities (Regions) in Spain.
List Spatial Options
Retrieves all possible geographic coverage boundaries for filtering data.
List Themes
Lists every available category or theme used to classify datasets in the catalog.
Search Datasets By Title
Searches the national catalog specifically by matching keywords against dataset...
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Datos.gob.es Catalog integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Datos.gob.es (Catálogo Nacional), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 22 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Sifting through government data is a nightmare of tabs and dropdown menus.
Today, finding specific public data means clicking through dozens of regional portals. You start at the national site, click 'Health', then narrow down by 'Andalucía,' but you might end up on an index page with no obvious search bar. You copy a keyword into one box, realizing halfway through that it needs to be filtered by publisher ID instead.
With this MCP, your agent handles all the clicks and cross-references behind the scenes. Instead of manual navigation, you just tell your AI client what you need—say, 'Unemployment stats for Valencia in CSV format.' The result is a clean list of candidate datasets, ready to be used.
Targeted Retrieval with `list_provinces` and `get_dataset`
The biggest time sink disappears: you never have to guess the correct geographic filter. Instead of trying different codes or names, the MCP lets your agent pull the definitive list using `list_provinces`, ensuring the subsequent search is accurate.
What's different now is that you move from vaguely browsing a topic to executing a precise query against validated data points. You get actionable metadata, not just links.
What your AI can actually do with this
This MCP lets you query the official Datos.gob.es API directly through your AI agent. Instead of navigating dozens of government websites—each with its own search system—you ask for what you need and get structured metadata back. You can find datasets across national, regional, and local administrations by filtering on everything from health or economy themes to specific provinces or publishers.
Whether you're looking at raw data distributions or just checking which organizations publish certain records, this MCP handles the complexity. By connecting through Vinkius, your AI client accesses the full catalog, meaning you don't have to worry about knowing where to start searching. You simply ask for a dataset—say, 'all pollution reports in Andalusia formatted as CSV'—and get a targeted list of candidates.
019e3887-2af6-7081-be6e-747f825fd1e6 
Here's how it actually works
The bottom line is that you tell your AI client what data point you're after, and it handles the complex filtering across Spain's public sector databases.
Subscribe to this MCP on Vinkius. This establishes the connection between your preferred AI client and the Datos.gob.es API.
Tell your agent exactly what you need—for instance, 'Find datasets about waste management in Valencia.'
The MCP executes the necessary filters (theme, region) against the national catalog and returns a list of matching dataset details.
Who is this actually for?
Anyone who needs to build a report or analysis using official Spanish government figures. This is for the researcher tired of manually cross-referencing multiple regional data sources, and the developer needing structured metadata for an application.
Tracks public sector transparency by comparing dataset availability or update frequency across different Autonomous Communities.
Quickly finds and inspects required datasets for reporting, filtering out noise using specific criteria like publisher ID or format (e.g., CSV).
Identifies specific API endpoints and metadata structures needed to integrate open government data into a new application.
What Changes When You Connect
You don't waste time browsing government sites. By using list_datasets_by_theme, you immediately focus on the correct topic, skipping hundreds of irrelevant results.
Pinpoint your search with geographical filters. Need health stats for Madrid only? Use list_provinces and then filter by that specific ID to cut down noise instantly.
Developers gain speed. Instead of guessing API endpoints, you can use get_dataset once you have the URI identifier, getting all the necessary metadata in one call.
Data format limitations disappear. If you know your final output needs to be CSV, you filter early using list_datasets_by_format, saving downstream processing steps.
The scope is always clear. Use list_publishers and list_public_sectors together to understand who generated the data, giving context to the figures themselves.
See it in action
Comparing regional spending on education
A policy researcher needs to compare educational budgets across multiple regions. Instead of visiting each region's site, they can use list_datasets_by_theme (filtering for 'Education') and then combine that search with the results from list_regions to get a unified list of candidate datasets.
Finding all raw transport data by format
A developer needs all available transportation data, but only in JSON for their application. They can use list_datasets_by_keyword ('transport') followed immediately by list_datasets_by_format (JSON) to build a targeted list of endpoints.
Checking data availability before writing code
A software engineer needs to know the exact structure and update cycle for unemployment figures. They use get_dataset with a known URI identifier, checking the returned metadata before writing any integration code.
Narrowing down complex datasets by geography
A student only cares about data from the Basque Country concerning tourism. They combine list_datasets_by_spatial (filtering for 'País Vasco') with a keyword search to isolate the most relevant records.
The honest tradeoffs
Over-relying on general searches
Searching only by keywords like 'health' and hoping it returns everything needed. This misses datasets that are categorized differently or require a specific publisher ID.
Always start with the taxonomy tools. First, use list_themes to confirm 'Health' is the right category. Then, refine your search using list_datasets_by_theme and restrict it by a relevant list_provinces result.
Ignoring data format requirements
Pulling a list of datasets that turns out to be in PDF or XML, forcing manual conversion before use.
Always include the file type filter. Use list_datasets_by_format first to ensure you only pull records available as CSV or JSON.
Assuming one tool covers everything
Thinking that just knowing a region name is enough for filtering, without checking the official list.
To be safe, always confirm valid inputs. Use list_regions or list_provinces to get the exact ID the API expects before passing it into any filter function.
When It Fits, When It Doesn't
Use this MCP if your goal is data discovery and structured filtering across Spain's public sector. You need an answer like: 'Which datasets exist that meet these three criteria?' Don't use it if you already have the raw API endpoint or if your task involves heavy visualization, cleaning, or merging of multiple disparate datasets using external logic. For pure data processing, you might only need a basic keyword search tool; however, this MCP is necessary because it gives you control over how that search happens—by letting you filter by theme, publisher, and region in the first place. If you just need to know what themes are available, check out list_themes before trying to find data.
Questions you might have
How do I find all datasets related to 'water management'? (list_datasets_by_keyword) +
You can use list_datasets_by_keyword for a broad search. This gives you initial candidates, but it's better practice to also run list_datasets_by_theme to ensure the results fall under the correct official category.
Can I filter data by multiple regions? (list_spatial_options) +
Yes. You use list_spatial_options to confirm the available boundaries, and then combine that knowledge when calling list_datasets_by_spatial. This lets you look at multi-regional comparisons.
What if I only know the publisher's name? (list_publishers) +
First, run list_publishers to get the exact ID. Then, use that precise ID in list_datasets_by_publisher. Using the ID is much more reliable than using a name.
Does this MCP handle data for private companies? (get_public_sector) +
No. This catalog focuses exclusively on public sector information from national, regional, and local administrations in Spain.
How do I use `list_datasets_by_format` to filter for specific file types like CSV or JSON? +
You pass the desired format (e.g., 'csv' or 'json') directly into the function call. This immediately filters the entire catalog, so you only get datasets containing that specific data type. It’s a fast way to narrow down your search results based on how you plan to consume the data.
I need data updated recently; can I use `list_datasets_by_date`? +
Absolutely, you specify a start and end date range when calling list_datasets_by_date. The MCP filters datasets that were modified within those parameters. This is crucial for research where knowing the update frequency matters.
What's the best way to get detailed metadata if I already have a dataset’s URI, using `get_dataset`? +
Simply pass the full URI identifier into get_dataset. This tool bypasses general searching and retrieves all core information about that single dataset. You'll get details like its issuing body, update frequency, and available distributions.
Before I filter geographically, how do I list all provinces using `list_provinces`? +
Run the list_provinces tool first. This gives you a definitive taxonomy of every province available in the catalog. After getting that list, you can use the specific IDs to filter your datasets by location.
How can I search for datasets containing a specific word in the title? +
Use the search_datasets_by_title tool. Provide the string you are looking for in the title parameter, and the agent will return all matching datasets from the national catalog.
Is it possible to filter datasets by a specific file format like CSV or JSON? +
Yes! Use the list_datasets_by_format tool and specify the format (e.g., 'csv', 'json', 'xlsx'). This will retrieve only the datasets that offer distributions in that format.
Can I find datasets belonging to a specific category like 'Health' or 'Environment'? +
Absolutely. Use the list_datasets_by_theme tool with the corresponding theme ID. You can first use list_themes to see all available categories in the catalog.
We've already built the connector for Datos.gob.es Catalog. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 22 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.