Dados RS MCP for AI. Query Rio Grande do Sul's Public Data Directly.

Q: How do I start finding data about education using searchdatasets?

Use searchdatasets with 'educação'. This will return all packages tagged or named related to education, giving you a list of options like 'Escolas Estaduais' to choose from.

Q: What is the difference between searchdatastore and searchdatastoresql?

searchdatastore handles simple keyword searches across existing data structures. searchdatastoresql lets you run custom, complex SQL queries for maximum control over your results.

Q: Can I use showorganization to find a specific dataset?

No. showorganization only gives details about the publishing body. You must first use listorganizations or searchdatasets to get the data package, then run showdataset to see who published it.

Q: How do I list all groups and their contents?

First, call listgroups. This gives you a master list of thematic categories. Then, if you want details on one group (e.g., 'Economy'), run showgroup.

Q: When should I use showresource versus running an SQL query with searchdatastoresql?

Use showresource to get metadata and understand a file's structure before using it. Use searchdatastoresql when you need to run complex operations directly on the raw, tabular data tables.

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.

Rio Grande do Sul (Dados RS) connects your AI client directly to the official public dataset portal. It lets you search, list, and query government records from Rio Grande do Sul without downloading files manually.

Use tools like `search_datasets` to find data on education or finance, or run complex SQL queries against the DataStore using `search_datastore_sql`.

This is direct access to state-level public information.

What your AI can do

Search datastore sql

Allows running custom, complex SQL queries directly against the raw data store.

Search datastore

Searches key terms across structured data tables in the DataStore.

List groups

Retrieves a list of thematic data groups (e.g., 'Environment' or 'Security').

+ 8 more capabilities included

Search available data packages

The agent finds multiple relevant public datasets across different topics using keyword searches.

Query raw database tables with SQL

You run complex Structured Query Language (SQL) commands directly against the DataStore to pull specific data points.

List all official publishing organizations

The agent retrieves a complete list of government bodies that manage and publish data on the portal.

View metadata for any dataset or resource

You get detailed information about a specific data package, including its resources, maintainer, and structure.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Rio Grande do Sul (Dados RS) MCP Server: 11 Tools for Data Query

Orchestrate every aspect of data exploration, from listing datasets and groups to running complex SQL queries against the core data store.

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 Rio Grande do Sul (Dados RS) on Vinkius

Search Datastore Sql

Allows running custom, complex SQL queries directly against the raw data store.

Search Datastore

Searches key terms across structured data tables in the DataStore.

List Groups

Retrieves a list of thematic data groups (e.g., 'Environment' or 'Security').

Show Group

Retrieves detailed information for a specified thematic data group.

List Organizations

Lists all government bodies that publish data on Dados RS.

Show Organization

Gets the profile and full details for a specific government organization.

List Datasets

Lists every public dataset available on the portal.

Search Datasets

Finds datasets by searching keywords or topics within the catalog.

Show Dataset

Pulls all the metadata and details about a specific, named dataset package.

Search Resources

Searches for specific individual files or metadata resources within a dataset.

Show Resource

Displays metadata and structure for an individual data file or resource attached to...

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 Dados RS 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": {
  "rio-grande-do-sul-dados-rs": {
    "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 Dados RS 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:

"rio-grande-do-sul-dados-rs": {
  "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 Rio Grande do Sul (Dados RS), 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 Dados RS. 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 11 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Finding state data used to be a pain in the neck.

Before this, finding public information meant bookmarking five different government websites. You'd click through group menus, cross-reference organization pages, and then download dozens of separate CSVs just to get one coherent picture—and you’d spend hours figuring out which file had the correct date range.

Now, your agent handles it. You tell it what you need, and it runs `search_datasets` across the entire catalog, pulling everything into a single, queryable list. It cuts the manual work down to seconds.

Using Dados RS with the `show_dataset` tool.

Previously, seeing how deep a dataset went meant clicking 'Resources' and then opening every single file link just to check if it was CSV or PDF. You had no idea what structure you were getting until you wasted time downloading junk files.

Now, calling `show_dataset` gives you the full metadata upfront. It shows the resource types (like CSV and PDF) and confirms ownership without opening a single page. It's instant verification.

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

Listen up. This Dados RS server connects your AI client right into the official public data portal for Rio Grande do Sul. It lets you work with government records without ever having to mess around downloading files manually. You're getting direct access to state-level public information, and it’s built entirely on tools so your agent can handle it.

When you need to find what kind of data exists out there, you start broad. Use list_datasets to get a master list of every single public dataset available on the portal. If you're looking for something more specific, search_datasets lets you pinpoint datasets just by throwing in keywords or topics—say, education or finance.

You can also narrow your search down using list_groups, which gives you thematic data groups like 'Environment' or 'Security,' or run list_organizations to see all the government bodies that publish this stuff.

Need to drill into what a specific dataset is about? Don't just rely on keywords. Use show_dataset to pull all the metadata and details for a package you found, which tells you everything about its resources and who maintains it. If you want to inspect an individual file or resource attached to a dataset, run show_resource to get its structure and metadata.

You can also check out the backstory using show_organization, which gives you a full profile for any government body that published data.

When discovery isn't enough, you gotta query the raw numbers. If you think certain keywords live inside structured tables in the DataStore, use search_datastore to search across those key terms directly. But if you need maximum power—the kind of deep dive that requires specific filtering and joining tables—you run complex Structured Query Language (SQL) commands with search_datastore_sql.

This tool lets your agent talk straight to the raw database layer, pulling exact data points you specify.

If you just want a comprehensive overview of every group or organization available on the portal, show_group pulls up detailed information for any specified thematic area. The whole point here is that your AI client doesn't guess; it executes these tools—from finding general packages with search_resources to running complicated SQL queries against the DataStore via search_datastore_sql—giving you structured results every time.

Built · Hosted · Managed by Vinkius Dados RS MCP Server - Query Brazilian Public Data

Server ID 019e38e4-cd4a-713b-94f2-93ec95cb478e

Vinkius Inspector

Compliance Grade A+

Score 98.33/100

Report View Report ↗

Here's how it actually works

The bottom line is: you talk to your agent, it talks to this server, and you get clean data structures back without touching a website GUI.

Your agent identifies the need (e.g., finding all education records).

It invokes the correct tool (search_datasets, list_organizations, etc.) with specific parameters.

The server connects to Dados RS and returns structured JSON data containing the requested metadata or query results.

Who is this actually for?

Data scientists, investigative journalists, and developers need this. It's for anyone who needs raw, verifiable government statistics from Rio Grande do Sul but is sick of manually clicking through 20 different web pages to piece together a story or build an app.

Data Scientist

You run search_datastore_sql to pull precise numbers for modeling, skipping the manual CSV download process.

Investigative Journalist

You use list_organizations and then query specific datasets (show_dataset) to audit public spending or government actions.

Developer

You integrate real-time data sources by calling tools like search_resources to feed live stats into an application API.

What Changes When You Connect

Stop guessing where data lives. Use search_datasets or list_groups to quickly narrow down public datasets by topic (like 'Health' or 'Economy').

Bypass the GUI entirely. Instead of clicking through filters, use search_datastore_sql to run precise SQL queries against the raw data layer.

Get full context before downloading. Run show_dataset or show_resource to inspect metadata and understand a file's structure first.

Map out who owns the data. Use list_organizations and then show_organization to trace which government body is responsible for specific records.

Find everything in one flow. Your agent can run search_datasets followed by show_resource to map a dataset down to its individual components, all in one chat session.

See it in action

01 01

Auditing public spending records

A journalist needs to track state revenue changes. Instead of manually navigating the finance portal, they ask their agent: 'Find all datasets related to state revenue.' The agent runs search_datasets and identifies 'receita-corrente-liquida'. They then use show_dataset to confirm it's from the correct source before pulling specific records.

02 02

Building a local data dashboard

A developer needs real-time educational stats. They instruct their agent: 'Get current school enrollment numbers.' The agent uses search_datastore to find relevant tables, and then runs a targeted query via search_datastore_sql to pull the exact counts needed for an API endpoint.

03 03

Mapping governmental data ownership

A researcher wants a full picture of environmental regulations. They start by running list_groups and narrow it to 'Environment'. Then they use search_datasets within that group, and finally run show_organization for each resulting dataset to determine which state body published the rules.

04 04

Verifying data completeness

A team wants to ensure all related stats are present. They ask their agent to list all datasets (list_datasets). Then, they check the organizations involved (list_organizations) and use show_organization for key players (like 'Secretaria da Saúde') to verify data coverage.

The honest tradeoffs

Treating search as a single command

Anti-pattern

Asking the agent, 'Find all data about health and education.' This vague prompt forces the model to guess which tools are needed and may miss specific datasets.

The Fix

Be explicit. Start by running list_groups to find the exact theme ('Health' or 'Education'), then use search_datasets with that group name for better results.

Skipping metadata inspection

Anti-pattern

The agent returns a list of datasets, and the user immediately tries to query them using search_datastore, potentially hitting an unusable data structure.

The Fix

Always run show_dataset on any promising result first. This checks the schema and resource count before you waste time running SQL.

Assuming dataset scope

Anti-pattern

The user thinks a single search (search_resources) will find everything related to a topic, but it only finds specific files, not the entire package.

The Fix

If you need broad coverage, start with search_datasets. If you only care about one file's metadata, then use show_resource.

When It Fits, When It Doesn't

Use this server if your process requires access to verifiable, raw public datasets from the Rio Grande do Sul government. You need a structured way to query records without manual web navigation.

Don't use it if you just need high-level summaries or visualizations (those are better handled by BI tools). Also, don't rely on it for data that isn't published via Dados RS. If your goal is simply 'find general information,' use a standard search engine; this tool is for structured data querying only.

Start with search_datasets to define the scope. If the dataset looks right, run show_dataset. Only hit the database hard with search_datastore_sql when you've confirmed the schema using show_resource first.

Questions you might have

How do I start finding data about education using search_datasets? +

Use search_datasets with 'educação'. This will return all packages tagged or named related to education, giving you a list of options like 'Escolas Estaduais' to choose from.

What is the difference between search_datastore and search_datastore_sql? +

search_datastore handles simple keyword searches across existing data structures. search_datastore_sql lets you run custom, complex SQL queries for maximum control over your results.

Can I use show_organization to find a specific dataset? +

No. show_organization only gives details about the publishing body. You must first use list_organizations or search_datasets to get the data package, then run show_dataset to see who published it.

How do I list all groups and their contents? +

First, call list_groups. This gives you a master list of thematic categories. Then, if you want details on one group (e.g., 'Economy'), run show_group.

What should I do if I hit rate limits when calling list_datasets? +

You need to provide your Dados RS API Key for higher rate limits. Adding the key ensures consistent data access, which is crucial when running many calls like listing all datasets or checking multiple resources.

When should I use show_resource versus running an SQL query with search_datastore_sql? +

Use show_resource to get metadata and understand a file's structure before using it. Use search_datastore_sql when you need to run complex operations directly on the raw, tabular data tables.

If search_datasets returns no results, does that mean the data doesn't exist? +

No; it usually means your search terms need refinement. Try using broader keywords or checking related thematic groups first via list_groups to narrow down your scope.

Does list_organizations only show government bodies, or does it include private sources? +

It lists official government organizations that publish public sector data. This server connects exclusively to the authorized open data portal for Rio Grande do Sul state records.

How can I search for datasets related to a specific topic like 'COVID'? +

Use the search_datasets tool with the q parameter set to your topic. For example, searching for 'covid' will return all matching packages from the portal.

Can I perform advanced data analysis using SQL on the portal's data? +

Yes! The search_datastore_sql tool allows you to execute full SQL SELECT statements against datasets stored in the CKAN DataStore, enabling complex filtering and aggregation.

How do I find which government departments are publishing data? +

Use the list_organizations tool to get a complete list of all government bodies. You can then use show_organization with a specific ID to see their metadata and datasets.

Connect to your AI in seconds.

Search datastore sql

Search datastore

List groups

Rio Grande do Sul (Dados RS) MCP Server: 11 Tools for Data Query

Make your AI actually useful.

Search Datastore Sql

Search Datastore

List Groups

Show Group

List Organizations

Show Organization

List Datasets

Search Datasets

Show Dataset

Search Resources

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

Finding state data used to be a pain in the neck.

Using Dados RS with the `show_dataset` tool.

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

Auditing public spending records

Building a local data dashboard

Mapping governmental data ownership

Verifying data completeness

The honest tradeoffs

Treating search as a single command

Skipping metadata inspection

Assuming dataset scope

When It Fits, When It Doesn't

Questions you might have