Comunidad de Madrid MCP for AI. Query official regional public records by conversation.

Q: How do I find all possible datasets using listdatasets?

You simply ask your agent to run listdatasets. This tool fetches every single dataset identifier the portal holds, giving you a master checklist of available regional data categories.

Q: Can I query raw numbers without downloading anything using searchdatastore?

Yes. That's exactly what searchdatastore does. Instead of manually grabbing and cleaning the figures from a CSV, you tell your agent which data points you need, and it pulls the numbers directly into your chat window.

Q: What is the difference between searchdatasets and getdataset?

searchdatasets finds potential datasets based on keywords. getdataset requires a precise ID and returns the full, detailed metadata for that specific dataset only.

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.

The Comunidad de Madrid Open Data Portal MCP lets your agent search and query official regional public records. Need to analyze air quality data or track public transport schedules? Connect it once, then use natural language to find datasets, inspect metadata, and pull content directly from the regional datastore.

What your AI can do

Get dataset

Retrieves the complete technical details and scope for one specific dataset ID.

Get resource

Gets metadata for a specific file or resource attached to a dataset (e.g., CSV, PDF).

List datasets

Lists the identifiers of every available dataset in the portal.

+ 2 more capabilities included

Find available datasets

List every dataset identifier currently indexed in the entire public portal.

Search for specific data topics

Filter and find relevant datasets using keywords related to a topic, like 'medio ambiente' or 'economía'.

Get dataset details

Retrieve the full metadata, including owners and update schedules, for one specific dataset.

Inspect individual files

Check the metadata for a particular resource within a dataset, such as an attached CSV or PDF file.

Query live data content

Run direct queries against the raw numbers inside a dataset's content store without needing to download anything.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Comunidad de Madrid (Portal Regional) - 5 Tools

These tools let you systematically navigate the open data portal: search for topics, list IDs, confirm metadata, inspect files, and query raw numbers.

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 Comunidad de Madrid (Portal Regional) on Vinkius

Get Dataset

Retrieves the complete technical details and scope for one specific dataset ID.

Get Resource

Gets metadata for a specific file or resource attached to a dataset (e.g., CSV, PDF).

List Datasets

Lists the identifiers of every available dataset in the portal.

Search Datasets

Filters and searches for datasets based on specific keywords or criteria you provide.

Search Datastore

Runs a direct query against the actual content of a dataset to pull raw data points.

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 Comunidad de Madrid 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": {
  "comunidad-de-madrid-portal-regional": {
    "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 Comunidad de Madrid 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:

"comunidad-de-madrid-portal-regional": {
  "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 Comunidad de Madrid (Portal Regional), 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 Comunidad de Madrid (Portal Regional). 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 5 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Dealing with regional data means jumping between dozens of government websites and downloading endless spreadsheets.

The old way is tedious: You start by searching the Madrid portal, finding a relevant topic like 'air quality.' Then, you click through to download the dataset metadata sheet—one file for tags, another for update frequency. You repeat this process across transport, health, and environment, copying identifiers and pasting them into a master spreadsheet just to see if they all use the same naming convention.

With this MCP, that entire multi-hour research session collapses into one conversation. Your agent figures out which datasets are related, finds the proper metadata using `get_dataset`, and most critically, it lets you run direct queries against the raw data content without ever needing to download a file.

The power of focused discovery with search capabilities.

You no longer waste time scrolling through thousands of irrelevant datasets. Instead, you just tell your agent what's wrong—maybe 'I need data on public buses in the north sector.' The system uses `search_datasets` to filter out everything else and give you a handful of highly relevant IDs instantly.

It’s not just finding the name; it's knowing the scope. You can use `get_resource` on those results to confirm if the specific file format (like JSON or CSV) is available before your agent even attempts to query the data. It saves you time and frustration.

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

This connector bridges your AI client to the Community of Madrid's open data portal. You gain access to a massive repository covering everything from health records and environmental reports to economic indicators and transportation logistics. Instead of clicking through complex government websites or downloading dozens of spreadsheets, you talk to your agent.

It handles the search logic for you. Your agent can find specific datasets by keyword—like 'salud' or 'transporte'—then pull the full metadata to show you exactly what's available. Even better, you don't have to download files manually; the data store allows direct querying of actual content, letting your AI client analyze the numbers right where they sit.

When connected through Vinkius, you get immediate access to this whole catalog, making regional analysis simple conversation.

Built · Hosted · Managed by Vinkius Madrid Open Data MCP - Query Regional Public Records

Server ID 019e387c-35ea-7353-8838-e01b886a0eca

Vinkius Inspector

Compliance Grade F

Score 3.6/100

Report View Report ↗

Here's how it actually works

The bottom line is, you tell your AI client what regional data you need, and it handles the complex search and retrieval process for you.

Subscribe to this MCP and optionally provide your Comunidad de Madrid API Key for better rate limits.

Tell your agent what you need; for example, 'Find all datasets about air quality' or 'Query the latest transport schedules.'

Your agent uses the appropriate tool—like search_datasets or search_datastore—to pull the information directly into the conversation window.

What Changes When You Connect

Stop manual downloads. Instead of downloading CSVs and struggling with headers, you use search_datastore to query the actual data content directly, letting your agent pull clean figures into your report.

Know exactly what's available. Use list_datasets first to see all dataset identifiers in the portal before committing to a search, giving you a full scope of regional information.

Quickly find relevant sources. If you know the general topic—say, 'salud'—you use search_datasets to narrow down thousands of records instantly, skipping weeks of manual browsing.

Get deep metadata without hassle. Once you identify a dataset ID using get_dataset, your agent pulls all the technical details (like update frequency and owner) in one step.

Better integration means less effort. By connecting this MCP through Vinkius, you get access to Madrid's full open data catalog from every compatible client, no matter where you code.

See it in action

01 01

Comparing air quality over time

A researcher needs to compare historical pollution levels across different districts. Instead of visiting several municipal sites, they ask their agent to find all environment-related data sources and use search_datasets to narrow it down. Then they run targeted queries using search_datastore for the specific time ranges needed.

02 02

Modeling public transport changes

An urban planner needs to know if new train lines correlate with demographic shifts. They first use list_datasets to map out available infrastructure data, then use get_dataset on the relevant transit dataset to confirm its scope before querying it for specific line identifiers.

03 03

Building a local health dashboard

A developer needs real-time metrics on healthcare resource availability. They ask their agent to find all 'health' related datasets, confirming the IDs with get_dataset, and then use search_datastore repeatedly to build a structured data output for an application.

04 04

Drafting a policy brief

A consultant needs recent economic indicators. They ask their agent to search using keywords like 'economía' or 'presupuesto', letting search_datasets filter the results, and then use get_resource on the most promising dataset to confirm if it contains the required file type (like a yearly PDF).

The honest tradeoffs

Searching without context

Anti-pattern

Asking your agent, 'Give me transport data.' The system might not know which dataset you mean and gives vague results.

The Fix

First, use search_datasets with keywords like 'transporte' to get a list of potential IDs. Then, ask the agent to run get_dataset on the most promising ID before trying to query it.

Downloading everything

Anti-pattern

Manually visiting five different government pages and downloading twenty separate JSON files just to find one metric.

The Fix

Use search_datastore. This tool queries the data directly, meaning you skip the download process entirely. You ask for the number, and it gives you the number.

Assuming a dataset exists

Anti-pattern

Calling get_dataset with an ID you heard about but never checked first; it fails because the identifier is wrong.

The Fix

Always start by using list_datasets, or better yet, use search_datasets to validate that the exact ID you need is active in the catalog.

Questions you might have

How do I find all possible datasets using list_datasets? +

You simply ask your agent to run list_datasets. This tool fetches every single dataset identifier the portal holds, giving you a master checklist of available regional data categories.

Can I query raw numbers without downloading anything using search_datastore? +

Yes. That's exactly what search_datastore does. Instead of manually grabbing and cleaning the figures from a CSV, you tell your agent which data points you need, and it pulls the numbers directly into your chat window.

What is the difference between search_datasets and get_dataset? +

search_datasets finds potential datasets based on keywords. get_dataset requires a precise ID and returns the full, detailed metadata for that specific dataset only.

Do I need to know the resource type before using get_resource? +

You don't. You just tell your agent which dataset you are looking at, and it uses get_resource to check metadata for specific file types—like confirming a PDF or CSV exists.

What happens if I hit rate limits when using `search_datasets`? +

The system will throw a rate limit error. To increase your query capacity, you can subscribe to the MCP and optionally input your Comunidad de Madrid CKAN API Key. This key significantly raises your allowable request volume.

When I use `get_dataset`, what specific details does the full metadata provide? +

The metadata gives you more than just a name; it lists tags, the owning organization, and how often the data updates. This helps you determine if the dataset is current or if it covers the scope you need.

For `get_resource`, do I need the full identifier for the file? +

Yes, pinpoint accuracy matters here. You must provide the specific resource ID and its associated dataset context. This ensures your agent retrieves the exact CSV or JSON file you're looking for.

I want to analyze data from several sources; should I use `list_datasets` first? +

No, listing every identifier is too much work. Instead, start by using search_datasets with keywords like 'transporte'. Once you find the right dataset ID, use search_datastore to query its content directly.

How can I find datasets about a specific topic like 'transport'? +

Use the search_datasets tool with the query 'transporte'. The agent will return a list of matching datasets with their unique IDs and descriptions from the portal.

Can I see the actual content of a data file without downloading it? +

Yes. If the resource is stored in the CKAN DataStore, you can use the search_datastore tool with the Resource ID to query the rows and columns directly.

Is an API key mandatory to use this server? +

No, it is optional. However, providing a CKAN_API_KEY allows for higher rate limits and access to restricted datasets if your account has permissions.

Connect to your AI in seconds.

Get dataset

Get resource

List datasets

Comunidad de Madrid (Portal Regional) - 5 Tools

Make your AI actually useful.

Get Dataset

Get Resource

List Datasets

Search Datasets

Search Datastore

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 regional data means jumping between dozens of government websites and downloading endless spreadsheets.

The power of focused discovery with search capabilities.

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

Comparing air quality over time

Modeling public transport changes

Building a local health dashboard

Drafting a policy brief

The honest tradeoffs

Searching without context

Downloading everything

Assuming a dataset exists

When It Fits, When It Doesn't

Questions you might have