Aragón Open Data MCP. Query regional public records directly from your AI agent
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Aragón Open Data. Connect your AI agent directly to the Government of Aragón's public data. This MCP server lets you query regional statistics, browse datasets, and inspect data schemas using natural language commands.
You can list all available views, search the CKAN catalog, and preview actual records without downloading CSVs. It's a direct pipeline to public governance data.
What your AI agents can do
Count datasets
Returns the total number of available datasets in the catalog.
Get dataset
Retrieves detailed information about a specific dataset package.
Get organization
Gets detailed information about a publishing organization or group.
Use search_datasets to find specific datasets, tags, or organizations by keyword across the entire public catalog.
Call list_views to get a complete list of all registered data views available in the system.
Use preview_data to fetch and display a sample of records from any given view or resource, supporting filtering.
Run show_columns to get the column names and data types for a specific data view, letting you validate the structure before querying.
Send a SPARQL query via query_sparql to run complex, graph-based queries against supported ontologies.
Retrieve specific metadata, such as using get_organization to find publisher details or get_dataset for package specifics.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
019e3866count datasets
Returns the total number of available datasets in the catalog.
019e3866get dataset
Retrieves detailed information about a specific dataset package.
019e3866get organization
Gets detailed information about a publishing organization or group.
019e3866get tag
Retrieves details for a specific data tag.
019e3866list datasets
Lists all available datasets (packages) in the catalog.
019e3866list groups
Lists all themes or groups used to categorize the data.
019e3866list organizations
Lists all publishing organizations that contribute data.
019e3866list tags
Lists all available data tags across the platform.
019e3866list views
Lists every available data view registered in Aragón Open Data.
019e3866most downloaded datasets
Retrieves a list of the most frequently downloaded datasets.
019e3866newest datasets
Retrieves a list of the most recently added datasets.
019e3866preview data
Fetches and displays a sample of records from a specified data view or resource.
019e3866query sparql
Executes a complex SPARQL query against the platform's knowledge graph.
019e3866search datasets
Searches the entire dataset catalog using keywords or filters.
019e3866show columns
Shows the names and data types of columns for a specific data view.
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 Aragón Open Data, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ 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
What you can do with this MCP connector
Aragón Open Data - Query Public Records MCP Server
Connect your AI agent straight to the Government of Aragón's public data. You can make your agent query regional statistics, look through datasets, and check data schemas using plain English. Your agent handles the heavy lifting; you don't have to download and process CSVs.
Searching the Data Catalog
You can find specific datasets, tags, or organizations by keyword across the whole public catalog using search_datasets. To see every dataset available, run list_datasets. You can also list all available data tags with list_tags, and see all contributing publishing organizations by calling list_organizations. If you're just looking for a quick count, count_datasets gives you the total number of available datasets.
Browsing and Listing Views
Use list_views to get a complete list of every registered data view in the system. You can also check which themes categorize the data by calling list_groups or see all of them with list_tags. To find out what's new or what people are using most, you've got newest_datasets and most_downloaded_datasets.
For specific packages, get_dataset retrieves detailed information, and you can get publisher details with get_organization or check a specific data tag with get_tag.
Inspecting and Previewing Data
When you're ready to see the data, preview_data fetches and displays a sample of records from any given view or resource, and it even handles filtering. Before you run a query, you can use show_columns to get the column names and data types for a specific data view, which lets you validate the structure.
If you need to run a complex, graph-based query, query_sparql executes a SPARQL query against the platform's knowledge graph.
Putting It Together
Your agent can list all views using list_views. It can then check the columns using show_columns. Next, it can pull a sample of records using preview_data. If you need to go deeper, you can execute a complex query with query_sparql. You can also search the whole catalog using search_datasets to narrow down your starting point.
It's a direct pipeline to public governance data, making the whole process straightforward.
How Aragón Open Data MCP Works
- 1 Subscribe to the server and provide your API key if required.
- 2 Tell your AI agent exactly what data you need (e.g., 'List all datasets about water quality').
- 3 Your agent selects and executes the necessary tool (
list_datasets,search_datasets, etc.) and returns the data structure directly.
The bottom line is that your agent translates natural language requests into specific API calls, fetching and structuring the public data for you.
Who Is Aragón Open Data MCP For?
Data Analysts, Researchers, and Developers. If your job involves finding, validating, or querying government or regional statistics, this is for you. You're the person who spends hours clicking through multiple departmental websites just to compile a simple data set. This server gives you a single conversational endpoint for all regional public records.
Prepares regional statistical reports by running preview_data on multiple views and compiling the results without manual CSV downloads.
Investigates public transparency issues by using search_datasets and list_groups to find relevant public records and organizational metadata.
Integrates data into applications by using show_columns and query_sparql to inspect API schemas and data structures directly in their development environment.
What Changes When You Connect
- See the full list of available views instantly using
list_views. Instead of navigating through a dozen departmental portals, your agent gives you every view ID in one go. - Skip the manual download process. With
preview_data, you get a sample of records from a view right in your chat, letting you validate the data before writing a single line of code. - Understand the data structure immediately. Use
show_columnsto get column names and data types for a view. This is faster than running a schema check in a separate database tool. - Run complex graph queries. The
query_sparqltool lets you use advanced SPARQL against ontologies like EI2A, letting you ask questions that simple keyword searches can't answer. - Find data fast. Instead of browsing, use
search_datasetsto pinpoint specific datasets or uselist_tagsandlist_groupsto narrow down your focus. - Get a high-level overview. Check
most_downloaded_datasetsto see what other analysts are using, helping you focus your research efforts.
Real-World Use Cases
Analyzing Housing Trends
A housing analyst needs to compare demographic data across multiple municipalities. They ask their agent, 'Show me all views related to housing.' The agent runs list_views, the analyst selects the relevant view ID, and the agent uses preview_data to pull the first 100 records, allowing for immediate comparison and validation.
Investigating Local Government Spending
A journalist is researching municipal spending. They tell their agent to search for 'Presupuestos Municipales' using search_datasets. The agent returns several hits, and the journalist uses get_dataset to confirm which package is the official source, saving hours of manual vetting.
Building a Data Pipeline
A developer needs to integrate local demographics into a new application. They ask the agent to inspect the structure of a view. The agent runs show_columns and provides the exact column names and data types, giving the developer the schema they need to start coding.
Advanced Topic Mapping
A researcher needs to find a relationship between air quality and urban development. They use query_sparql to write a graph query across multiple ontologies (like Aragopedia and ELI), retrieving complex, interconnected data points that simple table queries would miss.
The Tradeoffs
Using only keyword search
A user searches for 'climate data' using search_datasets and only sees a few results, thinking the catalog is incomplete.
→
First, use list_tags to see all available tags. Then, use list_groups to filter by 'Environment' before searching, which gives you a more comprehensive list of related resources.
Trying to dump all data
A user runs list_datasets and expects the full dataset content, leading to a timeout or a massive, unreadable list.
→
To see what's available, run list_datasets to get the package list. To see the data, use preview_data with specific filters and pagination, never trying to pull everything at once.
Ignoring the schema
A developer runs preview_data and sees data, but doesn't know if the 'Year' column is a string or an integer, causing code failures.
→
Before writing code, run show_columns on the view ID. This confirms the exact data type (e.g., integer, date) for every column, preventing runtime errors.
When It Fits, When It Doesn't
Use this server if your primary need is querying, browsing, or validating public, structured data from the Government of Aragón. You should use it when you need to know what data exists (list_views, list_datasets) or what the data looks like (preview_data, show_columns). Don't use it if you just need a simple list of names; use list_tags for taxonomy. If you need to connect to a private or internal company database, this server won't help — you'll need a dedicated internal API connector. If you need to run a complex, relationship-based query, you must use query_sparql because simple searches won't capture the necessary context. Never assume a dataset is complete just because it's listed; always validate the schema with show_columns first.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Aragón Open Data. 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 server provides 15 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Sifting through regional government data used to mean endless manual API calls and CSV downloads.
Before this server, getting regional statistics meant navigating the Aragón Open Data portal. You'd click through departmental sections, find a dataset package, and then run a specific API endpoint just to see the schema. It was a painful, multi-step process of copy-pasting IDs and dealing with pagination limits.
Now, your agent handles it all. You simply tell it, 'I need to compare housing demographics across these three zones.' Your agent uses `list_views` to find the correct views, then `preview_data` to fetch the necessary records, and presents the clean, structured output right in the chat. It's instant data access.
Aragón Open Data MCP Server: Structure and Schema Inspection
Manual data prep requires you to manually inspect every API endpoint to determine if the 'Year' column is a date object or just a string, and if the 'Municipality' field is consistent across all sources. This is a major bottleneck for developers.
Using the `show_columns` tool, you get the definitive schema for any view instantly. This capability lets you move straight to the code, knowing the exact data types and column names, and eliminating hours of schema guesswork.
Common Questions About Aragón Open Data MCP
Can I filter the data preview to see only specific records? +
Yes! Use the preview_data tool and provide a JSON string in the filters parameter (e.g., {"entidad": "ARANDA"}). This allows you to restrict the results to exactly what you need.
How do I find the structure and data types of a specific view? +
You can use the show_columns tool by providing the view_id. It will return a detailed list of all columns, their descriptions, and their technical data types.
Is it possible to search for datasets by keywords or topics? +
Absolutely. Use the search_datasets tool with the q parameter to perform a Solr search across the entire CKAN catalog for relevant datasets.
How do I use the `list_groups` tool to see all the data themes available? +
You use list_groups to get a list of all available themes or groups. This helps you narrow down your search before looking at specific datasets.
If I need to find datasets for a specific publisher, should I use `list_organizations` or `get_organization`? +
You should use list_organizations to see all available publishers. After that, you can use get_organization to fetch the detailed information for a specific publisher.
What should I do if my `preview_data` query fails or returns too much data? +
The preview_data tool supports filtering and pagination. You must specify filters or limit the results to prevent errors or overwhelming output.
Can I run complex queries using the `query_sparql` tool, and what ontologies does it support? +
Yes, query_sparql supports complex queries using ontologies like EI2A, Aragopedia, ELI, and DataCube. Just pass the necessary ontology context into your query.
Is there a way to find the most popular or newest datasets using the available tools? +
You can use most_downloaded_datasets to see the most popular datasets, or newest_datasets to find the most recently added ones.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Advice Slip
Universal advice engine — get random advice or search by keyword via AI.
Notion
Manage your Notion workspace, databases, and pages via AI.
Mem0
Give your AI agent persistent memory — store, search, and recall facts, preferences, and context across sessions using the leading agent memory platform.
You might also like
FeedBlitz
Manage mailing lists, RSS feeds, and email marketing campaigns through AI.
Blip
Build intelligent chatbots for WhatsApp, Messenger, and web that engage customers with conversational commerce flows.
Better Stack
Automate incident management via Better Stack — monitor uptime, manage incidents, and control on-call schedules securely from your AI agent.