Mato Grosso do Sul Open Data MCP for AI. Query state records using SQL or keyword search.

Q: How do I list all available datasets using the listpackages tool?

Call listpackages first. This returns a list of packages—think of them as high-level folders containing groups of data. You'll need to select one package ID from that list before you can query its contents.

Q: Can I use datastoresearch for complex joins?

No, datastoresearch is designed for simple keyword lookups within a single resource. For joining data across multiple sources or applying filters like 'AND' and 'OR', you must use the dedicated datastoresearchsql tool.

Q: What if I don't know the exact file structure?

Run getresource. Give it a specific resource link or ID, and this tool will pull the metadata, showing you exactly what fields are available. It's like getting the table of contents before reading chapters.

Q: Do I need to know every organization name?

Not necessarily. Use listorganizations first. This gives you a list of contributors, allowing you to narrow down your search scope and focus on the most relevant data sources for your project.

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.

Mato Grosso do Sul Open Data connects your AI client to public datasets from Mato Grosso do Sul, Brazil. It allows you to list data packages, search records in CSVs using keywords, or execute complex SQL queries against the raw state data store.

You don't need to download files; you just ask for the specific record set.

What your AI can do

Datastore search sql

Allows execution of custom SQL queries to select and filter specific columns from the data set.

Datastore search

Searches records across the data store based on general keywords provided by the user.

Get package

Retrieves detailed metadata about a single, specified dataset package by its identifier.

+ 4 more capabilities included

List all available datasets

Retrieves a list of every public data package hosted on the MS Open Data Portal.

Search records by keyword

Queries and finds specific entries within structured CSV or spreadsheet resources using natural language search terms.

Run advanced SQL queries

Executes complex, custom SQL statements against the data store to filter and analyze records (e.g., SELECT * FROM table WHERE value > 1000).

Get dataset metadata

Fetches detailed information—like schema or description—for a single, specified data package.

Identify data owners and groups

Lists the government organizations and internal working groups responsible for creating or maintaining the public records.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Mato Grosso do Sul Open Data: 7 Tools for Public Record Querying

Use these tools to manage metadata, search keywords, and execute custom SQL against public datasets from the Mato Grosso do Sul state portal.

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 Mato Grosso do Sul Open Data on Vinkius

Datastore Search Sql

Allows execution of custom SQL queries to select and filter specific columns from the data set.

Datastore Search

Searches records across the data store based on general keywords provided by the...

Get Package

Retrieves detailed metadata about a single, specified dataset package by its...

Get Resource

Pulls the structural details or schema for a specific file link within a larger data...

List Groups

Returns a list of all defined working groups associated with the open data records.

List Organizations

Lists every government organization that contributes data to the portal.

List Packages

Returns a complete list of all public dataset packages available for querying.

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 Mato Grosso do Sul 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": {
  "mato-grosso-do-sul-open-data": {
    "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 Mato Grosso do Sul 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:

"mato-grosso-do-sul-open-data": {
  "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 Mato Grosso do Sul Open Data, 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

Mato Grosso do Sul Open Data 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 Mato Grosso do Sul Dados Abertos. 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 7 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Collecting government statistics shouldn't require downloading ten separate ZIP files.

Today, pulling together state-level metrics means navigating dozens of departmental websites. You download a file from the 'Transportation' group, another from 'Health', and yet another from 'Revenue'. Then you have to manually unzip everything, open multiple Excel sheets, and cross-reference column headers just to build one basic comparison.

With this MCP server, your agent handles the whole process. Instead of managing downloads, you tell it: 'I need all records for X.' It uses `list_packages` and then targets the specific data with `datastore_search`, returning a clean, structured result set that’s ready to use.

Mato Grosso do Sul Open Data MCP Server: run complex SQL queries directly.

Without this tool, comparing two metrics (say, revenue vs. population) requires you to assume both datasets have the exact same column names and structure—a risky bet. You'd spend time cleaning up inconsistent naming conventions across sources.

Using `datastore_search_sql` lets you write a query that explicitly joins columns from multiple logical sources (even if they are in different conceptual tables), guaranteeing precise, controlled data extraction every single time.

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 Server gives your AI client direct access to public datasets from Mato Grosso do Sul, Brazil. You bypass the hassle of manually downloading files and filtering massive spreadsheets by letting your agent query the raw state data store directly.

When you use this server, your agent can perform three major functions: discovering available data, inspecting its structure, and executing specific queries against it.

To start, you need to know what records exist. You can run list_packages to pull a full inventory of every public dataset package hosted on the MS Open Data Portal. To figure out who owns that data or which department published it, your agent runs list_organizations for all contributing government entities and uses list_groups to list internal working groups responsible for maintaining those records.

Once you identify a potential dataset, you pull its full details using get_package, which fetches metadata about a single package. If you need to know the exact column names or format of a specific file linked within that set, run get_resource to pull the structural schema for that resource link.

For instance, if you're hunting for records related to water usage, and you suspect they come from a department called 'Environmental Services,' your agent can use list_organizations first. Then, it runs list_packages to narrow down the specific dataset package ID associated with that service area.

The core power of this server lies in querying the data itself. Instead of downloading everything and writing custom Python scripts, you just ask for what you need. You can run a general keyword search across structured CSV or spreadsheet resources using datastore_search. This tool lets you query records based on natural language terms—say, finding all entries mentioning 'irrigation pump' regardless of which column it appears in.

When the general search isn't precise enough, your agent hits the advanced tools. You execute complex, custom SQL queries directly against the raw data store using datastore_search_sql. This is where you filter and analyze records with precision; for example, writing a statement like SELECT * FROM agriculture WHERE yield > 500 AND year = 2023 tells the server exactly what records to pull.

It’s built for analysts who need reliable programmatic data collection without ever touching a download button.

The combination of these tools means your agent doesn't just read documentation; it acts like a database analyst, mapping out the available datasets, verifying their internal structure, and then pulling only the precise record set you requested. It keeps everything contained within the state’s public records environment.

Built · Hosted · Managed by Vinkius MS Open Data MCP Server - Query Brazilian State Records

Server ID 019e38be-e6a7-70e2-b91e-7560072ddc09

Vinkius Inspector

Compliance Grade F

Score 3.6/100

Report View Report ↗

Here's how it actually works

The bottom line is: it runs state-level queries against public records without needing an intermediary download step.

Subscribe to the server and provide your Mato Grosso do Sul Data Portal API Key.

Direct your AI client (Claude, Cursor, etc.) to run a data query using a specific tool name, like datastore_search or list_packages.

The agent executes the function call, fetches the raw public data through the server, and returns the filtered results directly to you.

Who is this actually for?

This is for data analysts, academic researchers, and developers who deal with large volumes of structured, publicly available government data. If your job requires correlating multiple datasets from a state portal, this saves hours of manual download management.

Data Analyst

Runs datastore_search to quickly find all records related to a specific project or geographic area without writing complex joins.

Academic Researcher

Uses list_packages and get_resource to automate the collection of public metadata needed for literature reviews or comparative studies.

Software Developer

Integrates real-time data into an application using datastore_search_sql, treating the state's database like a live backend endpoint.

What Changes When You Connect

Analyze raw data without downloading files. Instead of exporting a massive CSV and running local filters, use datastore_search to filter and retrieve the exact records you need right in your chat interface.

Write complex queries like a seasoned DBA. The datastore_search_sql tool lets you execute advanced SQL statements—like joins or aggregates—directly against the state data store. This is massive time savings.

Automate metadata collection. Use list_packages and get_package to build an inventory of all available datasets automatically, skipping the tedious process of manually visiting dozens of government web pages.

Understand data ownership instantly. Running list_organizations gives you a clear map of which state body is accountable for every dataset, improving research traceability.

Inspect data structures on demand. If you find a resource link but don't know its schema, get_resource tells you exactly what columns and fields are available before you try to query it.

See it in action

01 01

Tracking infrastructure spending

A researcher needs to compare construction spending across different municipal areas. They first use list_packages to find the right financial dataset, then they run a targeted datastore_search_sql query: SELECT * FROM 'finance-data' WHERE area = 'X' AND value > 10000. The agent returns only the relevant records for comparison.

02 02

Identifying data gaps

A developer needs to build an app that tracks public transportation. They run list_organizations to see which groups manage vehicle or route data, and then use get_resource on those organizations' datasets to map out the specific field names they need for their database model.

03 03

Comparing resource availability

A student is writing a paper comparing historical records. They first run list_packages to see all available time-series data, then use get_package on the relevant package to ensure it has enough granularity (e.g., daily vs. monthly) before committing to an analysis.

04 04

Finding specific incidents

An analyst suspects a record about 'Campo Grande' exists in a large, complex dataset. They don't know the exact table name, so they start by using datastore_search with the keyword 'Campo Grande'. The agent quickly returns matching records and their source package.

The honest tradeoffs

Using general chat for structure

Anti-pattern

Trying to ask, 'What are the columns in this dataset?' and waiting for a text answer. The agent might give you a paragraph that's hard to parse or use.

The Fix

Always call get_resource with the specific package ID first. That tool returns the precise, machine-readable schema, which is what your client needs.

Over-relying on simple search

Anti-pattern

Running datastore_search for a comparison (e.g., 'Compare revenue in 2021 and 2022'). Keyword searches are good for finding records, but bad for structured comparisons.

The Fix

Use the datastore_search_sql tool. Write a proper SQL query like SELECT * FROM data WHERE year IN (2021, 2022) to guarantee accurate columnar results.

Assuming all data is in one place

Anti-pattern

Asking for 'all government spending' without knowing the scope. You might miss vital information from a different department.

The Fix

Start by calling list_organizations to identify all contributing bodies, then systematically use get_package on each body's dataset package.

Questions you might have

How do I list all available datasets using the list_packages tool? +

Call list_packages first. This returns a list of packages—think of them as high-level folders containing groups of data. You'll need to select one package ID from that list before you can query its contents.

Can I use datastore_search for complex joins? +

No, datastore_search is designed for simple keyword lookups within a single resource. For joining data across multiple sources or applying filters like 'AND' and 'OR', you must use the dedicated datastore_search_sql tool.

What if I don't know the exact file structure? +

Run get_resource. Give it a specific resource link or ID, and this tool will pull the metadata, showing you exactly what fields are available. It's like getting the table of contents before reading chapters.

Do I need to know every organization name? +

Not necessarily. Use list_organizations first. This gives you a list of contributors, allowing you to narrow down your search scope and focus on the most relevant data sources for your project.

How do I authenticate before running a query with datastore_search? +

You must supply your Mato Grosso do Sul Data Portal API Key in the server configuration. Without this key, any tool call will fail immediately with an authentication error.

Can datastore_search_sql handle complex data types like dates or coordinates? +

Yes, it supports standard SQL functions for date manipulation and geometry queries. Use the 'YYYY-MM-DD' format to ensure accurate filtering on time-series records.

What happens if I run get_resource with an invalid ID? +

The tool returns a clear 404 error indicating the resource was not found. Before querying, check the parent package metadata using get_package to verify the correct link.

Are there rate limits when calling list_packages repeatedly? +

The server follows the official API rate limit policy of the state portal. For high-volume data collection, your agent needs to implement an exponential backoff strategy.

How do I find specific datasets about health or education? +

Use the list_packages tool to see all available dataset names, then use get_package with a specific ID to see the resources and descriptions related to that topic.

Can I perform complex filtering on the data records? +

Yes! Use the datastore_search_sql tool to execute standard SQL queries (e.g., SELECT, WHERE, GROUP BY) directly against the DataStore resources for precise analysis.

How do I see which government departments provide the data? +

Use the list_organizations action. It will return a list of all state entities and departments that have published data on the portal.

Connect to your AI in seconds.

Datastore search sql

Datastore search

Get package

Mato Grosso do Sul Open Data: 7 Tools for Public Record Querying

Make your AI actually useful.

Datastore Search Sql

Datastore Search

Get Package

Get Resource

List Groups

List Organizations

List Packages

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

Collecting government statistics shouldn't require downloading ten separate ZIP files.

Mato Grosso do Sul Open Data MCP Server: run complex SQL queries directly.

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

Tracking infrastructure spending

Identifying data gaps

Comparing resource availability

Finding specific incidents

The honest tradeoffs

Using general chat for structure

Over-relying on simple search

Assuming all data is in one place

When It Fits, When It Doesn't

Questions you might have