Valencia Open Data MCP for AI. Query City Records by Conversation.

Q: How do I start looking at all available datasets using listpackages?

You simply ask your agent to use listpackages. This returns a comprehensive list of every official dataset name, which is the first step in knowing what data exists on the portal.

Q: What if I need to find records within a specific dataset? Should I use searchdatastore?

Yes, that's right. Use searchdatastore. It lets you run powerful queries against the actual content of the resource, allowing you to filter by keywords or criteria.

Q: Do I need to know what group a dataset belongs to? Can listgroups help?

Using listgroups is helpful because it organizes the data. Instead of looking at thousands of datasets, you can filter them immediately by thematic categories like 'Traffic' or 'Health'.

Q: Is showresource always necessary before searching?

It’s highly recommended. showresource confirms the specific file format and field names within a dataset, preventing failures when you try to use searchdatastore.

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.

Gobierno Abierto Valencia connects your AI agent directly to the official city data portal. Use this MCP to query public datasets, inspect resource metadata, and search actual records from Valencia's open data resources using natural conversation.

What your AI can do

Search datastore

Searches for actual records within a resource’s data store using filters or keywords.

List groups

Retrieves a list of high-level organizational groups or categories for the datasets.

Show package

Gets detailed metadata for a specific dataset, including all its resources.

+ 2 more capabilities included

Find available datasets and groups

List the entire inventory of public data packages or narrow down the search by thematic category.

Check dataset details

Retrieve full metadata for a specific dataset, showing all its included resources and formats.

Inspect resource structure

Examine the internal file format, data types, and descriptions of any given resource within a package.

Search specific records

Run advanced queries against the actual stored data points inside a resource using filters or keywords.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Gobierno Abierto Valencia: 5 Tools

These tools let you inventory, inspect, and search the entirety of Valencia's publicly available dataset resources.

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 Gobierno Abierto Valencia on Vinkius

Search Datastore

Searches for actual records within a resource’s data store using filters or keywords.

List Groups

Retrieves a list of high-level organizational groups or categories for the datasets.

Show Package

Gets detailed metadata for a specific dataset, including all its resources.

List Packages

Lists all available dataset names that you can query.

Show Resource

Retrieves deep information on a single file, detailing its structure and format.

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 Valencia Open Data 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": {
  "gobierno-abierto-valencia": {
    "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 Valencia Open Data 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:

"gobierno-abierto-valencia": {
  "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 Gobierno Abierto Valencia, 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 Gobierno Abierto Valencia. 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.

Sifting through official data portals is a pain.

Right now, finding specific public records means clicking around massive government websites. You find the main portal, then you have to guess if your info is under 'Transportation' or maybe 'Infrastructure.' Then you land on a package list and realize the dataset you need is nested three layers deep, forcing you to download large files just to check one column.

With this MCP, that manual effort vanishes. You talk to your agent; it finds the right data source instantly. Instead of dealing with folders and downloads, you get direct answers by querying the structured records using `search_datastore`.

The power of `show_resource` lets you verify data structure.

You used a dataset name that looks right, but before running a search, you need to know what the columns are called. You can't assume every resource has a 'date' column; it might be 'fecha' or something else entirely. Manually checking these details is tedious and prone to error.

Now, run `show_resource` first. It gives you the complete breakdown of that file’s structure—the data types, formats, and fields—so your subsequent searches are guaranteed to hit the mark.

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 connection lets you treat Valencia’s massive collection of civic and municipal data like a simple database lookup. Instead of navigating dozens of web pages or downloading ZIP files just to find one number, you talk to your agent. It finds the right dataset—whether it's public transit schedules or historical spending records—and gives you the details without manual effort.

You can ask about specific groups of data or search deep inside a resource’s actual record set using simple questions. When you connect this MCP through Vinkius, you get immediate access to thousands of other specialized tools alongside Valencia’s open data, all managed in one place.

Built · Hosted · Managed by Vinkius Valencia Open Data - Query Public City Records

Server ID 019e38a0-bbb4-7088-9c87-a6ce097d85d4

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

What Changes When You Connect

Skip manual browsing. Instead of clicking through multiple tabs, you ask the agent to list all available datasets or narrow down results by group using list_groups or list_packages.

Understand data structure instantly. Use show_resource to check if a dataset contains GPS coordinates or time stamps before attempting to search it.

Run complex searches without code. The search_datastore tool lets you filter records using natural language, finding specific information like 'all buses on route 12' immediately.

Drill down efficiently. After identifying a package with show_package, you can see all the different resources it holds (CSV, JSON, etc.) and pick exactly what you need.

Save time on data discovery. You get to skip the tedious process of manually correlating dataset names with their actual content by using this single MCP connection.

See it in action

01 01

Finding Transit Schedule Data

A developer needs real-time bus schedules for a new app feature. Instead of searching the Valencia website's documentation, they ask their agent to list packages and then use show_package to pinpoint the correct dataset, ensuring it supports GeoJSON format.

02 02

Verifying Historical Budgets

A researcher wants to see how much money was allocated to parks in 2018. They use list_groups to find 'Budget' records, then run a targeted query with search_datastore filtering by year and department.

03 03

Checking Data Integrity

A data analyst finds a dataset but isn't sure if it has location data. They use show_resource to inspect the metadata, confirming that the available format includes latitude and longitude fields before committing to analysis.

04 04

Discovering Relevant Data Sources

A citizen wants general information on all municipal transparency records. They start by asking the agent to list groups; this quickly narrows their focus from 'everything' to specific thematic categories.

The honest tradeoffs

Searching everything at once

Anti-pattern

Asking, 'Tell me about Valencia data.' This returns a massive block of unrelated information and is impossible for the agent to process correctly.

The Fix

First, use list_groups to narrow your focus (e.g., 'Transportation'). Then, if you need specifics, list packages or search the datastore with filters.

Assuming format

Anti-pattern

Trying to run a complex query on a dataset when you don't know if the records are in JSON or CSV. The tool will fail mysteriously.

The Fix

Always use show_resource first. This tells you exactly what data formats and fields are available before you try to pull any actual records.

Ignoring category structure

Anti-pattern

Sending a vague request for 'city info' without knowing if the city categorized it by 'Infrastructure' or 'Environment'.

The Fix

Start with list_groups. This gives you the official categories used by the portal, making your requests precise and actionable.

When It Fits, When It Doesn't

Use this MCP if your problem involves accessing specific, structured public records from Valencia's open data portal. You need to query datasets or search records that already exist online. Don't use it if you are looking for general civic knowledge, articles, or news reports—that’s a text retrieval task. If you only want to see what kind of data exists, start with list_groups and then move to show_package. Never try to search the datastore without first confirming the resource's structure using show_resource; otherwise, your query will fail due to incorrect field names.

Questions you might have

How do I start looking at all available datasets using list_packages? +

You simply ask your agent to use list_packages. This returns a comprehensive list of every official dataset name, which is the first step in knowing what data exists on the portal.

What if I need to find records within a specific dataset? Should I use search_datastore? +

Yes, that's right. Use search_datastore. It lets you run powerful queries against the actual content of the resource, allowing you to filter by keywords or criteria.

Do I need to know what group a dataset belongs to? Can list_groups help? +

Using list_groups is helpful because it organizes the data. Instead of looking at thousands of datasets, you can filter them immediately by thematic categories like 'Traffic' or 'Health'.

Is show_resource always necessary before searching? +

It’s highly recommended. show_resource confirms the specific file format and field names within a dataset, preventing failures when you try to use search_datastore.

How do I get the full metadata for a specific dataset using show_package? +

It pulls all necessary metadata, giving you an overview of the data structure and formats before you start querying. This shows you available fields (columns) and resource types within that package.

What kind of filtering can I apply when running a query with search_datastore? +

You can apply powerful filters, date ranges, and multiple criteria simultaneously. This lets your agent narrow down records without needing to download the entire dataset first.

What happens if my AI client calls any tool without a valid API Key? +

The call fails immediately with an authentication error. You must ensure your agent is provided the correct, active Valencia Open Data API key for successful data retrieval from this MCP.

If I'm looking for public records in a niche category, should I use list_groups first? +

Yes, that’s the best starting point. By listing groups, you narrow down the scope quickly, helping your agent focus on relevant datasets and saving time.

How do I search for specific records within a data file? +

Use the search_datastore tool with the specific Resource ID. You can provide a search string q to filter the records and use limit or offset for pagination.

How can I see the metadata for a specific dataset? +

Simply use the show_package tool and provide the name or ID of the dataset. The agent will return full metadata including descriptions, maintainers, and associated resources.

Can I list all the data categories available in the portal? +

Yes! The list_groups tool returns all dataset groups or categories available in the Valencia Open Data portal, helping you browse by topic.

Connect to your AI in seconds.

Search datastore

List groups

Show package

Gobierno Abierto Valencia: 5 Tools

Make your AI actually useful.

Search Datastore

List Groups

Show Package

List Packages

Show Resource

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 official data portals is a pain.

The power of `show_resource` lets you verify data structure.

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

Finding Transit Schedule Data

Verifying Historical Budgets

Checking Data Integrity

Discovering Relevant Data Sources

The honest tradeoffs

Searching everything at once

Assuming format

Ignoring category structure

When It Fits, When It Doesn't

Questions you might have