Acre Dados Abertos MCP for AI. Query Brazil's public sector data from one place.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Acre Dados Abertos lets your AI agent query public datasets from the State of Acre, Brazil. This MCP allows you to search for specific government packages by topic, check detailed metadata on resources, and filter records directly within large tables without downloading gigabytes of files.
It connects complex state-level data into simple conversations.
What your AI can do
Get group
Retrieves specific details about a single thematic group (e.g., 'Health' or 'Economy').
Get package
Fetches the detailed metadata for one specific dataset package.
Get resource
Gets technical information about a single data file or resource within a dataset.
You list every major topic area (like 'Health' or 'Economy') published by the state government.
Your agent searches for packages using keywords to pinpoint relevant data sets, like GDP reports or demographic statistics.
You fetch technical details about any file—its format, source, and how it was created—before you even use the data.
Your agent searches inside large CSV files by applying filters (e.g., 'only show Rio Branco for 2020'), so you don't download the whole thing.
Ask an AI about this
Waiting for input…
Acre Dados Abertos: 8 Tools
These tools give your agent the power to list groups, search packages, check metadata, and query specific data records from the Acre open data 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 Acre Dados Abertos on VinkiusGet Group
Retrieves specific details about a single thematic group (e.g., 'Health' or 'Economy').
Get Package
Fetches the detailed metadata for one specific dataset package.
Get Resource
Gets technical information about a single data file or resource within a dataset.
List Groups
Lists every major thematic group available in the Acre open data catalog.
List Organizations
Shows all government organizations that publish data through the portal.
List Packages
Lists every available dataset package name in the system.
Search Datastore
Filters and finds specific records inside a large, tabular resource without downloading the entire file.
Search Packages
Searches across all available datasets for packages that match your keywords.
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 Acre Dados Abertos integration is available immediately — no restart needed.
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
Make Your AI Do More
Start with Acre Dados Abertos, 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 Acre 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
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.
The Headache of Manual Data Collection
Today, pulling public sector data means navigating a maze. You start by finding the right department's portal, then drilling down through folders and tabs until you find a giant CSV file. If that one file doesn't have exactly the column you need, you spend hours downloading it, opening it in Excel, and manually filtering out every row of junk data.
With this MCP, your agent handles the whole process. You just ask for the metrics; the tool automatically finds the correct packages using `search_packages`, pulls the metadata with `get_package` to confirm its quality, and uses `search_datastore` to give you only the filtered numbers you need. It's done in conversation.
The power of structured data discovery via list_groups
Before this MCP, figuring out what kind of public data existed was guesswork; you had to try searching multiple departments hoping one held the answer. Now, running `list_groups` gives you a clear map—a single view of every major thematic area published by the state.
You're no longer guessing which folder has the answers. You immediately know if the data is organized under 'Health' or 'Economy,' making your research systematic and predictable.
What your AI can actually do with this
Need to pull figures from a Brazilian government report? You don't have to manually navigate dozens of departmental websites or download massive ZIP archives just to find one number. This MCP lets your agent talk directly to the Acre Dados Abertos portal, treating it like a structured database you can query in natural language.
Instead of browsing by folder structure and hoping the right data is inside, your AI client handles the discovery process for you. It finds specific datasets, checks who published them, and even filters records within those tables using specialized tools. You connect this MCP via Vinkius, giving any compatible agent instant access to thousands of public records across different sectors like health or education.
Your agent acts as a research assistant, finding the data points so you can focus on what you're actually writing.
019e3860-1486-71be-a9f3-572d598a8919 
Here's how it actually works
The bottom line is you give your agent the question; it handles the complex data portal navigation and extraction process for you.
Subscribe to this MCP and connect it to your preferred AI client.
(Optional) Enter an Acre API Key into the connection settings for higher query limits.
Ask your agent a question like, 'Show me all datasets related to education in Acre.' The agent then uses the available tools to browse and filter the public records.
Who is this actually for?
Journalists, academic researchers, and business analysts who rely on public sector statistics. If you spend time manually clicking through government websites to build a report, this is for you.
Verifies specific government figures or finds public records related to municipal spending without calling three different data departments.
Samples and filters multiple disparate datasets for a report, comparing environmental trends across different regions in one workflow.
Builds a literature review by listing all thematic groups available on the portal to ensure no relevant data is overlooked.
What Changes When You Connect
You don't download massive files. By using search_datastore, your agent filters records inside large tables, giving you only the exact rows you need.
Finding related datasets is fast. Instead of browsing folders, use list_groups to see every available thematic area and then focus your search.
You get context on the data source immediately. Using get_resource lets you check the file format and provenance before committing to a query.
It handles the bureaucracy of government portals. Your agent manages the difference between listing organizations using list_organizations versus finding specific reports via search_packages.
The whole process is conversational. You just ask your AI client, 'Find me data on X,' and the MCP figures out which tools to run behind the scenes.
See it in action
Comparing municipal spending year-over-year
A data analyst needs to compare education funding across four different municipalities for five years. They instruct their agent to use search_datastore on the relevant package, specifying filters by municipality and year, avoiding manual exports.
Verifying a journalist's claim about environmental policy
A journalist wants proof of resource allocation for Amazonian conservation. They ask their agent to first use list_groups to find 'Environment,' then run search_packages within that group, and finally retrieve the metadata using get_package on the most promising hit.
Mapping all available data sources for a project
A developer needs to know every potential data source before coding. They ask their agent to run list_groups and list_organizations, providing them with a full, categorized inventory of what's available.
Deep dive into a single record's history
A researcher finds one interesting data point. They use the resource ID to run get_resource immediately, verifying if the file is an official CSV or just a PDF summary before continuing their research.
The honest tradeoffs
Searching everything with one keyword
Asking your agent to 'show me all data.' This vague prompt forces the system to guess and results in an overwhelming list of general packages, wasting time.
Instead, first use list_groups to narrow it down. Then, ask the agent to run search_packages within that specific group for better focus.
Trying to download everything
If you just need one column of data from a 10-year report, downloading the entire CSV is slow and inefficient.
Use search_datastore. This tool allows filtering by specific columns (like 'State' and 'Year') directly on the server side, giving you only the necessary records.
Getting stuck between groups and organizations
Not knowing whether to list all publishing bodies or find a topic area. You might run list_organizations when you really need data from the 'Education' group.
Always start by running list_groups first. This gives you the thematic buckets, and then you can use get_group to explore what's inside.
When It Fits, When It Doesn't
Use this MCP if your goal is to find, inspect, or query structured public data published by government bodies in Acre. You need specific datasets (packages) or deep filtering within large tables (datastores). Don't use it if you are looking for general news articles, unstructured text documents, or information that isn't tied to a formal dataset structure. If your problem is 'I want to find out what happened,' this MCP won't help; you need a web search tool. But if your problem is 'What were the exact figures on X in Y year?'—this is exactly what you need.
Questions you might have
How do I find a dataset related to my topic using search_packages? +
You simply ask your agent to run search_packages with keywords. The tool scans the entire catalog of datasets and returns matching packages, saving you from manually checking every department.
Does get_resource help me if I don't know the file format? +
Yes. You pass the resource ID to get_resource, and it pulls the technical metadata for that specific file, telling you exactly what kind of data it is (CSV, JSON, etc.).
Can I filter large files without downloading them using search_datastore? +
Absolutely. That's the point of search_datastore. You give your agent a resource ID and filtering criteria—like 'Rio Branco' and '2019'—and it returns only those specific, filtered records.
What is the difference between list_groups and list_organizations? +
Use list_groups when you want to browse by topic (like education or health). Use list_organizations when you need to know which specific government body published the data.
What do I need to use my own API key when running list_groups? +
You can optionally provide an Acre API Key for higher rate limits. This key ensures your queries aren't restricted by default usage caps, giving you reliable access even with heavy data exploration.
How do I find out what kind of organization published a dataset using get_package? +
The get_package tool provides detailed metadata about the package, including its originating government body. This helps you trace the data's provenance and understand who was responsible for publishing it.
If I want to see all available datasets first, should I use list_packages or search_packages? +
Use list_packages if you just need a comprehensive list of every dataset name. If you know keywords, search_packages is faster because it lets your agent filter the results immediately.
After I find a thematic group using list_groups, how do I see what specific data resources are inside? +
Once you have identified the theme via list_groups, you should use get_group with that group's ID. This will show all associated datasets and organizations relevant to your topic.
How can I search for datasets related to a specific topic like 'health'? +
Use the search_packages tool with the query 'saude'. The agent will return a list of datasets matching that theme from the Acre portal.
Can I filter data inside a CSV file without downloading it? +
Yes! If the resource is in the Datastore, use the search_datastore tool with the Resource ID. You can apply filters like {"municipio": "Rio Branco"} to get specific rows.
How do I find which government departments are publishing data? +
Use the list_organizations tool to see all contributing entities, or list_groups to see thematic categorizations like 'Environment' or 'Economy'.
We've already built the connector for Acre Dados Abertos. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 8 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.