# Aragón Open Data MCP for AI Agents AI Agent Connect

> Aragón Open Data MCP gives your AI agent direct access to the Government of Aragón's public records. Query datasets, preview specific records, and search the CKAN catalog without leaving your chat or editor. It turns regional government data into a searchable knowledge base for your projects.

## Overview
- **Category:** knowledge-management
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_U2FrehT9ZwKWDKtgZlyI9Q4wBfp7a5oWuyuR4Hyg/ai-agent-connect
- **Tags:** open-data, aragon, ckan, public-records, data-exploration

## Description

Aragón Open Data is an Connector that links your AI client to the regional government's public information portal. Instead of hunting through complicated government websites or manually downloading CSV files to see what's available, you can just ask your agent to find specific records. It works by pulling data from the GA_OD_Core and CKAN catalogs, making it easy to see what the region is publishing on topics like public spending, demographics, or local infrastructure. You can have your agent look up the structure of a dataset to see what columns exist before you start pulling data, or ask it to find the most popular files in the region. It's a practical way to get real-time government transparency data into your workflow. If you're looking for a way to pull regional statistics into a project, finding it through the Vinkius catalog makes the connection quick and reliable. You get answers to specific questions about local governance and public records without the usual friction of manual data gathering.

## Tools

### count_datasets
Get the total count of datasets available in the portal. This helps you understand the scale of the available information.

### get_organization
Retrieve details about a specific publisher or government organization. Use this to find who manages a specific data source.

### get_dataset
Fetch full details for a specific dataset package. This provides the metadata needed to understand a specific record set.

### get_tag
Get the specific details for a data tag. This helps clarify how certain records are categorized.

### list_groups
List all themes and groups in the catalog. Use this to browse different categories of regional data.

### list_organizations
List all publishers and organizations. This gives you an overview of all government entities sharing data.

### list_datasets
List all datasets available in the catalog. Use this to see the full scope of public data.

### list_views
List all available views in Aragón Open Data. Use this to see specific data perspectives.

### most_downloaded_datasets
Get a list of the most popular datasets. This helps identify the most relevant and frequently used records.

### newest_datasets
Get the most recently added datasets. Use this to stay updated on new government transparency data.

### list_tags
List all tags used in the system. This is useful for finding all possible ways to filter the data.

### preview_data
Preview the first 1000 records from a specific view. This lets you see the actual content before making a decision.

### query_sparql
Execute a SPARQL query against regional ontologies. This is for advanced queries on specific data structures.

### search_datasets
Search for specific datasets using keywords. This is the fastest way to find a specific topic in the catalog.

### show_columns
Get information about the columns for a specific view. This is essential for understanding the data schema.

## Prompt Examples

**Prompt:** 
```
What are the newest datasets from the Government of Aragón?
```

**Response:** 
```
I've pulled the most recently added records from the catalog. Here are the latest datasets:

| Dataset Name | Date Added | Category |
| :--- | :--- | :--- |
| *Example Dataset A* | 2024-05-10 | Environment |
| *Example Dataset B* | 2024-05-08 | Infrastructure |

Would you like more details on any of these?
```

**Prompt:** 
```
Show me the columns for the 'Censo de Viviendas' view.
```

**Response:** 
```
I've inspected the schema for the 'Censo de Viviendas' view. It includes the following columns:

* **Municipio** (Text)
* **Año** (Integer)
* **Valor** (Float)
* **ID_Registro** (String)

Would you like me to preview some records from this view?
```

**Prompt:** 
```
Find all datasets related to tourism.
```

**Response:** 
```
I searched the catalog for 'turismo' and found several relevant datasets:

* **Ocupación Turística**
* **Red de Oficinas de Turismo**
* **Estadísticas de Visitantes**

Would you like to see the details for one of these, or should I search for a different keyword?
```

## Capabilities

### Fetch regional dataset counts
Get the total number of datasets available in the portal instantly.

### Preview first 1000 records
See a sample of the data from a specific view or resource.

### Inspect column names and types
Understand the data structure of a specific view before you use it.

### Search the entire catalog
Find datasets, tags, or organizations using keyword queries.

### Execute SPARQL queries
Run complex queries on regional ontologies like Aragopedia.

### Retrieve publisher information
Get details about the organizations and themes that publish data.

## Use Cases

### Journalist investigation
A reporter asks for all datasets related to tourism to find local stats. The agent uses search_datasets to find the relevant records.

### Developer schema check
A developer wants to see the columns for Air Quality before writing a script. The agent uses show_columns to provide the schema.

### Data analyst summary
An analyst asks for the most downloaded datasets to see what is popular. The agent uses most_downloaded_datasets to pull the list.

### Researcher deep dive
A researcher uses SPARQL queries to find specific links between regional ontologies using query_sparql.

## Benefits

- Skip manual CSV downloads by using preview_data to see records instantly.
- Understand data structures faster with show_columns to check schemas before you start.
- Find relevant records faster using search_datasets to filter by tags or organizations.
- Identify popular regional trends by calling most_downloaded_datasets directly.
- Access complex regional ontologies using query_sparql for deep data analysis.
- Get a bird's eye view of regional themes with list_groups to see what's available.

## How It Works

The bottom line is you get direct, natural language access to the Government of Aragón's public data catalog.

1. Subscribe to the Aragón Open Data MCP and get your API key from the official portal.
2. Connect the Connector to your preferred client like Claude or Cursor.
3. Ask your agent to find, preview, or query specific government datasets.

## Frequently Asked Questions

**Does Aragón Open Data MCP let me see real records?**
Yes, it allows your agent to fetch and preview actual records from the government's public views, typically showing the first 1000 records so you can see the real content.

**Can I use Aragón Open Data MCP to find specific regional statistics?**
Exactly. You can ask your agent to search for specific topics like demographics, spending, or environmental data and it will pull the relevant datasets for you.

**How does Aragón Open Data MCP help with government transparency?**
It provides a direct line to public records. You can quickly see what organizations are publishing data and what themes they cover without manual browsing.

**Can I see the data structure before downloading it?**
Yes, you can ask your agent to show you the columns and data types for any specific view. This ensures you know exactly what the data looks like before you use it.

**Does Aragón Open Data MCP support complex queries?**
Yes, it supports SPARQL queries, which allows for advanced analysis of regional ontologies like Aragopedia and DataCube.

**Is there a way to see the most popular datasets?**
Yes, the Connector can identify the most downloaded datasets in the region, helping you see which public records are currently most in demand.

**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.