Dades Obertes Catalunya MCP for AI. Query Catalonia's public government data with natural language.

Q: How do I find the unique identifier for a specific dataset?

Use the searchcatalog tool with a descriptive query. The response will include the 4x4 alphanumeric ID (e.g., 'abcd-1234') which you can then use with the querydataset tool.

Q: Can I filter data by specific values like a city or a date range?

Yes! When using querydataset, use the $where parameter to apply SoQL filters. For example, $where: "poblacio > 5000" or $where: "comarca = 'Barcelonès'".

Q: Is a Socrata App Token mandatory to use this server?

No, it is optional. However, providing a DADESAPPTOKEN allows for higher rate limits and prevents throttling during intensive data exploration.

Q: When I use querydataset, how do I handle extremely large result sets?

Use the $limit and $offset parameters. You can request results in controlled batches to manage memory and ensure you process every record systematically without overwhelming your client.

Q: What kind of metadata does searchcatalog return so I know if a dataset is right for me?

searchcatalog provides the dataset's official identifier, its associated categories, and a brief description. This lets you verify the data source before attempting any complex queries.

Q: How do I perform a general keyword search across all columns using querydataset?

You need to use the $q: parameter instead of filtering with $where:. This allows you to run full-text searches, finding records based on keywords across multiple fields.

Q: Before running querydataset, how do I use searchcatalog to narrow down my research area?

When using searchcatalog, specify keywords or categories in your prompt. This narrows the catalog from thousands of records, allowing you to select only the precise dataset ID you need.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

Dades Obertes Catalunya lets your agent search and query thousands of public datasets from Catalonia's official open data portal. Use natural language to find relevant dataset IDs via `search_catalog`, then use those identifiers with `query_dataset` to filter, select specific columns, and extract structured information on topics like health, transport, or demographics.

What your AI can do

Query dataset

Runs advanced queries against a specific dataset using complex filters and selection parameters.

Search catalog

Searches the full open data catalog to find relevant datasets by keyword or category name.

Search for public datasets

Find the unique identifiers needed to query by searching the Dades Obertes Catalunya catalog using keywords or categories.

Query specific data records

Filter and retrieve structured rows from any dataset by applying complex criteria, selecting only the columns you need, and sorting results.

Analyze grouped statistics

Group raw data results to calculate or summarize metrics across entire datasets on demand.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Dades Obertes Catalunya: 2 Tools for Data Discovery

These two tools let you first locate the right open data catalog, and then run complex, filtered queries against that 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 Dades Obertes Catalunya on Vinkius

Query Dataset

Runs advanced queries against a specific dataset using complex filters and selection parameters.

Search Catalog

Searches the full open data catalog to find relevant datasets by keyword or category...

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 Dades Obertes Catalunya integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "dades-obertes-catalunya": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Dades Obertes Catalunya tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"dades-obertes-catalunya": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

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

Start building

Make Your AI Do More

Start with Dades Obertes Catalunya, 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

Dades Obertes Catalunya MCP server cover

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Dades Obertes Catalunya. 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

Your data is protected. See how we built it.

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 2 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Dealing with public government statistics used to be a huge headache.

If you're doing research, you know the drill: You have to jump between ten different municipal websites. You find one dataset, download it as a CSV, open it in Excel, and then try to copy relevant columns into your master spreadsheet. Then you repeat that process for the next department.

Now? You just ask your agent what data you need from the entire catalog. It finds the source ID, runs the complex query for you, and hands over a clean table of exactly what you asked for. No manual downloading, no formatting headaches.

Querying specific public data with `query_dataset`

Writing complex filters or joins used to require knowing the exact schema of a dataset and writing specialized query language. If you missed one column name, your whole analysis failed.

This MCP handles that complexity for you. You simply describe the relationship—'show me all records where location X is in province Y'—and the system executes the accurate database logic behind the scenes.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

Need to pull public statistics from the Government of Catalonia? This MCP lets your agent browse thousands of government datasets without you having to manually navigate dozens of websites. You start by searching the entire catalog using keywords—it'll point you toward the right dataset ID. Once you have that identifier, you can run complex queries against it in natural language.

For instance, you can ask the system to find all records about electric vehicle charging stations within a specific postal code and only show the location and power rating. The whole process happens through your AI client, which handles the underlying data structure. Vinkius makes connecting this open data platform easy, letting any MCP-compatible client run sophisticated queries that used to require an actual database expert.

You just talk to it.

Built · Hosted · Managed by Vinkius Dades Obertes Catalunya - Query Public Government Data

Server ID 019e3884-9543-70b9-9a8f-bb8998926b4e

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

Here's how it actually works

The bottom line is: your AI client handles all the back-and-forth of data discovery and querying so you just get the final, filtered list.

First, subscribe to this MCP. You can optionally add a Socrata App Token if you plan on making heavy queries.

Next, tell your AI client what kind of data you need (e.g., 'datasets about hospital populations'). The agent uses the search_catalog tool to find relevant IDs.

Finally, give the system the target ID and the specific filters or metrics you want. The agent executes a query using query_dataset and returns the results.

What Changes When You Connect

Stop manually downloading spreadsheets. Use search_catalog to find the right dataset ID, then use query_dataset to pull exactly the columns and rows you need in one go.

Filter massive datasets instantly. Instead of writing complex SQL syntax, ask your agent to 'show me records where population is over 10k' using the query function.

Cross-reference multiple data points easily. You can find identifiers for transport routes and then immediately query them against demographic data in a single workflow.

Get structured results right away. The system handles grouping and limiting, giving you clean, actionable lists without needing to write any aggregation code yourself.

Saves research time. Instead of wasting hours navigating government portals, you let your agent do the searching and querying for you.

See it in action

01 01

Analyzing urban growth trends

A researcher asks their agent to find datasets related to 'urban planning' using search_catalog. They then use that ID with query_dataset to filter for records where the year is between 2010 and 2015, getting a clean list of growth metrics.

02 02

Checking infrastructure capacity

A developer needs data on electric vehicle charging stations. They use search_catalog to find the relevant dataset ID, then run a query to see all records where 'power_kw' is above 50 and group them by location.

03 03

Comparing public health metrics

A data analyst wants to compare hospital capacity across regions. They use search_catalog for 'health centers,' get the ID, and then query it using query_dataset with complex filtering on location and date ranges.

04 04

Finding demographic information

A student needs to know population trends. They ask their agent to search the catalog for 'demographics,' get the ID, and then query it to show them the top 5 records sorted by the largest population count.

The honest tradeoffs

Trying to write custom API calls

Anti-pattern

The user manually tries to build a complex URL with filters and limits based on documentation, which is prone to syntax errors.

The Fix

Let your agent handle it. First, use search_catalog to confirm the correct dataset ID. Then, tell your AI client what you want (e.g., 'show me all records where X is true')—the agent uses query_dataset correctly.

Forgetting to narrow down the scope

Anti-pattern

The user asks for 'all data' without specifying a date range or column, resulting in an overwhelming dump of records.

The Fix

Always be specific. Tell your agent exactly what you need: Use query_dataset and specify $where: "date >= 2020" to limit the scope.

Assuming data is available in a single source

Anti-pattern

The user thinks all transport data is in one place, leading to incomplete research.

The Fix

Use search_catalog first. It helps you find multiple related datasets (e.g., finding separate catalogs for 'trains' and 'buses') that you can then query separately.

Questions you might have

How do I find the unique identifier for a specific dataset? +

Use the search_catalog tool with a descriptive query. The response will include the 4x4 alphanumeric ID (e.g., 'abcd-1234') which you can then use with the query_dataset tool.

Can I filter data by specific values like a city or a date range? +

Yes! When using query_dataset, use the $where parameter to apply SoQL filters. For example, $where: "poblacio > 5000" or $where: "comarca = 'Barcelonès'".

Is a Socrata App Token mandatory to use this server? +

No, it is optional. However, providing a DADES_APP_TOKEN allows for higher rate limits and prevents throttling during intensive data exploration.

When I use `query_dataset`, how do I handle extremely large result sets? +

Use the $limit and $offset parameters. You can request results in controlled batches to manage memory and ensure you process every record systematically without overwhelming your client.

What kind of metadata does `search_catalog` return so I know if a dataset is right for me? +

search_catalog provides the dataset's official identifier, its associated categories, and a brief description. This lets you verify the data source before attempting any complex queries.

How do I perform a general keyword search across all columns using `query_dataset`? +

You need to use the $q: parameter instead of filtering with $where:. This allows you to run full-text searches, finding records based on keywords across multiple fields.

If my AI client fails when using `query_dataset`, what is the first thing I should check? +

Check your usage against the API's standard rate limits. While basic access works, applying a Socrata App Token dramatically increases throughput and prevents connection failures.

Before running `query_dataset`, how do I use `search_catalog` to narrow down my research area? +

When using search_catalog, specify keywords or categories in your prompt. This narrows the catalog from thousands of records, allowing you to select only the precise dataset ID you need.

Connect to your AI in seconds.

Query dataset

Search catalog

Dades Obertes Catalunya: 2 Tools for Data Discovery

Make your AI actually useful.

Query Dataset

Search Catalog

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Dealing with public government statistics used to be a huge headache.

Querying specific public data with `query_dataset`

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Analyzing urban growth trends

Checking infrastructure capacity

Comparing public health metrics

Finding demographic information

The honest tradeoffs

Trying to write custom API calls

Forgetting to narrow down the scope

Assuming data is available in a single source

When It Fits, When It Doesn't

Questions you might have