- ORG LIST
- DATA MAP
- GAP ANALYSIS
- HUMAN REVIEW
Short answer
How do I find which government bodies own specific datasets?
Your AI uses this MCP to pull a list of all active organizations in the portal. It then drills into specific agencies to see what they publish. You get a clear map of data ownership and availability.
Where your findings land.
The outcomes of your search.
The AI organizes the portal's structure into these categories.
ORG LIST
Agency directory
The AI identifies every government body listed in the portal. You get a clean list of names to use for your research.
DATA MAP
Dataset ownership
The AI links specific datasets to their responsible agencies. This tells you exactly who manages the information you need.
GAP ANALYSIS
Missing information
By comparing agency lists against available files, the AI flags where data might be missing. You decide how to address these gaps.
HUMAN REVIEW
Validation required
The AI flags complex or nested organizational structures that need a person to verify the context. You handle the final interpretation.
The workflow
What your AI does when the request arrives.
The AI moves from broad discovery to specific data inspection.
Catalog agencies
The AI scans the portal to build a complete list of all participating government organizations.
list_organizationsInspect departments
Once an agency is identified, the AI looks inside that specific organization to see its published content.
show_organizationMap data owners
The AI correlates the datasets found with the specific agency responsible for them.
show_organizationSummarize findings
The AI compiles the agency names and their respective data types into a structured report.
list_organizations
Try it
Copy these to start.
Use these prompts to begin your data mapping.
Starting points
Replace the bracketed text with the specific agency or topic you are looking for.
Dados RS Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_8wKN6HQka16PPK7UOkRk0TJP6qVXaLeeEAEEiu66/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Dados RS capabilities are ready to use.
{
"mcpServers": {
"rio-grande-do-sul-dados-rs-mcp": {
"url": "https://edge.vinkius.com/vk_preview_8wKN6HQka16PPK7UOkRk0TJP6qVXaLeeEAEEiu66/mcp"
}
}
}List all the organizations available in the Rio Grande do Sul data portal.
Show me the datasets published by the Secretaria da Fazenda.
Which government bodies in Rio Grande do Sul publish environmental data?
Find all organizations related to public health and list their available datasets.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Rio Grande do Sul (Dados RS) once, then ask.
One connection gives your AI access to the portal. Your credentials stay encrypted and secure, and you can start asking questions immediately.
Connect Rio Grande do Sul (Dados RS) to your AIFAQ
How this task behaves.
- 01
Can the AI download the actual CSV files?
No. The AI can see the metadata and information about the datasets, but it cannot download or manipulate the files themselves.
- 02
Can the AI add new datasets to the government portal?
No. This MCP is read-only. It can only see what is already published by the government.
- 03
Does the AI know about data not listed in the portal?
No. The AI only knows about the organizations and datasets it can find through the provided tools.
- 04
Can I use this to find contact info for agency heads?
Only if that contact information is part of the organization's published metadata in the portal.
- 05
Will the AI update the data if it changes?
The AI sees the data as it exists at the moment you run the command. It does not track changes automatically.
More questions about Rio Grande do Sul (Dados RS)? The Connector page answers them. See everything the Rio Grande do Sul (Dados RS) Connector can do
Connect Dados RS to Claude, Cursor, ChatGPT & more
