Ayuntamiento de Madrid MCP for AI. Find and inspect city data metadata instantly.

Q: How do I find datasets related to 'transport' using madridsearchpackages?

You must use madridsearchpackages and specify that filter. You can pass in the group name or relevant tags alongside your query to narrow down results effectively.

Q: What is the difference between madridgetpackage and madridgetresource?

The madridgetpackage tool gives you details about the whole dataset container. The madridgetresource tool only provides metadata for a single file—like a specific CSV or JSON sheet—within that package.

Q: Can I find which departments publish data using madridlistorganizations?

Yes. Running madridlistorganizations gives you the definitive list of municipal departments, allowing you to map data sources by their source agency name.

Q: How do I use madridlisttags when I don't know what specific topic I need?

madridlisttags returns a comprehensive list of all keywords used across the portal. You can review these tags to narrow down your research before running a targeted query.

Q: What is the difference between using madridlistpackages and searching with madridsearchpackages?

madridlistpackages gives you a full inventory of every single available dataset name. Using madridsearchpackages, however, lets you filter that inventory based on criteria like tags or groups.

Q: When should I use madridlistgroups versus listing all packages with madridlistpackages?

Use madridlistgroups when you need to browse data by a major municipal division. Use madridlistpackages if you want an absolute, raw list of every dataset available in the system.

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.

Ayuntamiento de Madrid (CKAN) MCP connects directly to the official open data portal of the Madrid City Council. Use this connector to search, categorize, and retrieve metadata for thousands of public datasets covering everything from city transport and environmental reports to municipal budgets.

You can list all available packages or drill down into specific resources using natural language queries.

What your AI can do

Madrid get package

Retrieves the complete technical metadata for a single specified dataset package.

Madrid get resource

Fetches the detailed metadata for one specific file or resource within a dataset.

Madrid list groups

Lists all major categories or groups of data available in the catalog.

+ 5 more capabilities included

Discover all datasets

List every package or search for groups using keywords like 'environment' or 'transport'.

Examine dataset metadata

Retrieve deep details on any specific dataset, including its maintainer and usage license.

Identify and check files

Find individual files (like CSV or JSON) within a dataset and get their specific resource metadata.

Map city departments

List all municipal organizations that contribute data to the portal, helping you trace information sources.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Ayuntamiento de Madrid (CKAN) with 8 Tools

These tools let you programmatically interact with the city's entire data catalog, allowing deep metadata retrieval and targeted searching.

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 Ayuntamiento de Madrid (CKAN) on Vinkius

Madrid Get Package

Retrieves the complete technical metadata for a single specified dataset package.

Madrid Get Resource

Fetches the detailed metadata for one specific file or resource within a dataset.

Madrid List Groups

Lists all major categories or groups of data available in the catalog.

Madrid List Organizations

Provides a list of all municipal departments that publish open data to the portal.

Madrid List Packages

Generates a simple list of every available dataset name in the entire catalog.

Madrid Search Packages

Searches for specific datasets, supporting filtering by groups and tags using a query string.

Madrid Search Resources

Allows searching across resources based on defined criteria to find specific files.

Madrid List Tags

Lists all current tags or keywords used to categorize data across the city’s records.

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 Ayuntamiento 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": {
  "ayuntamiento-de-madrid-ckan": {
    "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 Ayuntamiento 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:

"ayuntamiento-de-madrid-ckan": {
  "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 Ayuntamiento de Madrid (CKAN), 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 Ayuntamiento de Madrid. 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 8 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Sifting through municipal data is typically tedious work.

Before this MCP, gathering city information meant opening the official portal and clicking through multiple directories. You’d scroll past dozens of irrelevant datasets—things like old zoning maps or niche department reports—just to find a small file on public transport usage. Every search required manually verifying the dataset's license and checking if the data was updated recently.

Now, you just ask your agent what you need. It uses the MCP to check the index instantly, providing only the most relevant packages. You get immediate metadata, confirming the source, update cycle, and file format in one query.

Ayuntamiento de Madrid (CKAN) MCP: Immediate Data Discovery

The manual steps of navigating category pages (`madrid_list_groups`) and then running keyword searches are gone. You tell your agent the topic, and it runs `madrid_search_packages` directly to surface candidates.

It’s a major change. Instead of spending time mapping out where the data lives on the website, you get straight to the metadata—the actionable intelligence about the dataset.

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 MCP lets you query Madrid’s massive open data collection without needing to visit the official website. Instead, you ask your AI client questions about city services, and it finds the right datasets for you. Need to know what departments publish data? You can list all municipal organizations. Want details on a specific dataset's license or update frequency? It pulls that metadata instantly.

Whether you’re analyzing air quality trends or tracking public transport usage, this tool provides real-time access to city records. By connecting through Vinkius, you gain immediate access to the entire catalog of Madrid's publicly available information, allowing your agent to perform complex data discovery and resource identification right where you are working.

Built · Hosted · Managed by Vinkius Madrid Open Data - Dataset Metadata Finder MCP

Server ID 019eb8a5-a8c0-737d-be3a-fc7f1fc05a3b

Vinkius Inspector

Compliance Grade A

Score 90/100

Report View Report ↗

Here's how it actually works

The bottom line is you get structured access to Madrid’s public information that would otherwise require manual searching across multiple web pages.

Subscribe to this MCP and enter your API Key from the Madrid Data portal (if required for certain endpoints).

Direct your AI client to use the madrid_search_packages or madrid_list_groups tool, specifying the city data query.

Your agent returns a list of datasets, metadata details, or resource IDs based on the API's live response.

Who is this actually for?

This MCP targets data professionals and academics. It's for the urban planner who needs to find specific environmental datasets or the developer who has to integrate city-provided metadata into an application without leaving their IDE.

Data Analyst

Uses madrid_search_packages to locate and validate municipal datasets for trend analysis, filtering results by tags or groups.

Urban Researcher

Employs the list functions like madrid_list_organizations to map out data sources when studying city services or economic impact areas.

Software Developer

Calls madrid_get_resource and retrieves IDs and metadata, allowing them to programmatically integrate specific public files into an application stack.

What Changes When You Connect

Pinpoint exact datasets: Use madrid_search_packages to filter thousands of records by topic (e.g., transport, environment), saving hours of manual browsing time.

Trace data sources: The madrid_list_organizations tool tells you exactly which city department maintains the information, crucial for citation and reliability checks.

Deep metadata access: Instead of just seeing a file name, use madrid_get_package to get full context on dataset ownership, update frequency, and licensing requirements.

Resource precision: Need a specific CSV? Use madrid_search_resources or madrid_get_resource to identify the exact file metadata, bypassing general searches entirely.

Understand categorization: List all available groups with madrid_list_groups to understand how the city structured its data before you even begin querying.

See it in action

01 01

Analyzing air quality changes over time

An environmental researcher needs to track pollution levels across different Madrid districts. They ask their agent to find datasets by calling madrid_search_packages with 'air quality' and then use madrid_get_package on the result to confirm the data fields match their study criteria.

02 02

Integrating city budget data into a dashboard

A developer must pull financial records for an application. Instead of navigating complex forms, they use madrid_list_organizations to find the 'Finance Department' and then search for packages using that source identifier.

03 03

Checking resource availability for a report

A journalist needs data on bike-share usage. They first call madrid_search_packages for 'BiciMAD', and then use madrid_get_resource to confirm the existence and format of the most recent usage log file.

The honest tradeoffs

Over-relying on listing tools

Anti-pattern

Asking the agent to run madrid_list_packages, then reading every single result, and trying to manually filter for 'transport'.

The Fix

Don't list everything. Use targeted searching instead. Call madrid_search_packages and pass in the appropriate tag or group name (e.g., 'transport') directly.

Confusing package with resource

Anti-pattern

Assuming that listing a dataset's metadata (madrid_get_package) means you can download every file without checking which files exist.

The Fix

Always follow up by calling madrid_search_resources or madrid_get_resource. This confirms the specific, available files (CSV/JSON) and their individual IDs.

Not specifying a filter

Anti-pattern

Running a general search without narrowing down by tags or groups.

The Fix

Always use filtering parameters. If you know it's about environment, call madrid_search_packages and include the relevant group name to keep results precise.

When It Fits, When It Doesn't

Use this MCP if your primary need is metadata discovery—you want to know what data exists, who made it, and what format it's in. It is excellent for initial research or architectural planning.

Don't use this if you already have the specific dataset ID and only need simple API calls to download a known file. For that, a dedicated storage connector might be better. Also, don't assume the tools cover every relationship; they are focused on package/resource discovery, not complex joins between datasets.

When in doubt about scope, start with madrid_list_groups or madrid_list_tags to map the data landscape before attempting a deep search.

Questions you might have

How do I find datasets related to 'transport' using madrid_search_packages? +

You must use madrid_search_packages and specify that filter. You can pass in the group name or relevant tags alongside your query to narrow down results effectively.

What is the difference between madrid_get_package and madrid_get_resource? +

The madrid_get_package tool gives you details about the whole dataset container. The madrid_get_resource tool only provides metadata for a single file—like a specific CSV or JSON sheet—within that package.

Can I find which departments publish data using madrid_list_organizations? +

Yes. Running madrid_list_organizations gives you the definitive list of municipal departments, allowing you to map data sources by their source agency name.

Do I need an API key for madrid_search_packages? +

While some endpoints require keys, your agent handles the authentication process. Always check the documentation if specific endpoints fail; sometimes a key is needed to run searches against certain restricted datasets.

How do I use madrid_list_tags when I don't know what specific topic I need? +

madrid_list_tags returns a comprehensive list of all keywords used across the portal. You can review these tags to narrow down your research before running a targeted query.

If I only have a resource ID, how does madrid_get_resource help me inspect that specific file's metadata? +

You provide the unique resource ID directly. The tool then fetches all associated details for that single file or data asset without needing to know which larger dataset it belongs to.

What is the difference between using madrid_list_packages and searching with madrid_search_packages? +

madrid_list_packages gives you a full inventory of every single available dataset name. Using madrid_search_packages, however, lets you filter that inventory based on criteria like tags or groups.

When should I use madrid_list_groups versus listing all packages with madrid_list_packages? +

Use madrid_list_groups when you need to browse data by a major municipal division. Use madrid_list_packages if you want an absolute, raw list of every dataset available in the system.

How can I find datasets specifically about air quality or pollution? +

You can use the search_packages tool with a query like 'aire' or 'contaminacion'. The agent will return a list of matching datasets available in the Madrid portal.

Can I get the direct download link for a data file? +

Yes. By using get_package or get_resource, the agent will provide the metadata which includes the 'url' field for the specific resources (CSV, PDF, etc.) associated with that dataset.

How do I see which municipal department published a certain dataset? +

Use the get_package tool for a specific dataset ID. The metadata returned will include the organization name. You can also use list_organizations to see all publishing entities.

Connect to your AI in seconds.

Madrid get package

Madrid get resource

Madrid list groups

Ayuntamiento de Madrid (CKAN) with 8 Tools

Make your AI actually useful.

Madrid Get Package

Madrid Get Resource

Madrid List Groups

Madrid List Organizations

Madrid List Packages

Madrid Search Packages

Madrid Search Resources

Madrid List Tags

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

Sifting through municipal data is typically tedious work.

Ayuntamiento de Madrid (CKAN) MCP: Immediate Data Discovery

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 air quality changes over time

Integrating city budget data into a dashboard

Checking resource availability for a report

The honest tradeoffs

Over-relying on listing tools

Confusing package with resource

Not specifying a filter

When It Fits, When It Doesn't

Questions you might have