Inep Dados Abertos MCP for AI. Query Brazil's educational statistics instantly.
Works with every AI agent you already use
…and any MCP-compatible client








Connect to your AI in seconds.
Inep Dados Abertos connects your AI client directly to Brazil’s official educational data portal. You can query massive datasets like Censo Escolar, ENEM results, and IDEB statistics using natural language or SQL-like queries; no manual downloading required.
This MCP lets you find specific microdata points across multiple years and map organizational structures within the Brazilian Ministry of Education.
What your AI can do
Get group
Retrieves full details about a specific group within the INEP structure.
Get organization
Gets detailed information for any registered department or body in INEP.
Get package
Fetches metadata and details about a specific educational dataset package.
List all high-level educational packages and organizations within the INEP system.
Get specific details about a dataset, including download links or structural information for CSVs and PDFs.
Find specific datasets or tags by searching the catalog's descriptive index.
Run structured, SQL-like commands to filter and extract rows from large internal data stores.
Fetch specific information about groups or organizations by their unique IDs.
Ask an AI about this
Waiting for input…
Inep Dados Abertos MCP with 12 Tools
These functions let your agent list datasets, search metadata, retrieve package details, run SQL queries against live data stores, and map the organizational structure of INEP.
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 Inep Dados Abertos on VinkiusGet Group
Retrieves full details about a specific group within the INEP structure.
Get Organization
Gets detailed information for any registered department or body in INEP.
Get Package
Fetches metadata and details about a specific educational dataset package.
Get Resource
Retrieves structural information for an individual data file or resource within a...
List Groups
Lists all available groups defined within the INEP catalog.
List Organizations
Provides a list of departments that contribute data to INEP.
List Packages
Lists all available educational dataset packages (like ENEM or IDEB).
List Tags
Retrieves a list of predefined tags used to categorize INEP data.
Search Datastore Sql
Runs advanced queries using SQL syntax against the raw data in a datastore.
Search Datastore
Searches for specific pieces of information directly within a large, live dataset...
Search Packages
Searches across all available dataset packages by name or keyword.
Search Resources
Finds specific data files or components within the INEP catalog structure.
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.
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 Inep 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 Inep. 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 12 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Dealing with Brazil's educational data means endless tabs and massive file downloads.
Right now, if you need to compare exam scores across states, you’re probably clicking through dozens of INEP portals. You download a gigantic zip, then another one for the year after that. Then you spend hours cleaning up conflicting column names and trying to merge everything into a single spreadsheet.
With this MCP, you don't deal in files; you deal in answers. You simply tell your agent what comparison you need—say, 'Compare IDEB scores between SP and RJ for 2015.' The system pulls the data directly from the sources using the right functions.
Search Datastore SQL: Running precise queries against millions of records
The manual process requires you to download a resource, open it in Excel or Pandas, and write complex filtering logic yourself. You're limited by what the file structure shows you on screen.
Here’s the difference: `search_datastore_sql` lets your agent execute real SQL commands against the data store. It acts like having a dedicated database administrator running the query for you; it delivers precisely the rows and columns you request.
What your AI can actually do with this
This connector gives your agent direct access to some of Brazil's most detailed educational data. Forget spending hours navigating complex government websites or wrestling with huge, raw CSV files. Instead, you ask for exactly what you need—say, 'What was the average exam score in São Paulo for public schools in 2018?'—and get a targeted answer.
The system handles the deep dive into millions of records across various academic packages and resources. It’s all managed through Vinkius; you just connect your preferred AI client and start asking questions. You can search, inspect metadata, or run specific queries to pull out exactly the data points you need for any kind of reporting or research.
019e38ad-34af-71e5-80b4-14aad6ba2d5f Here's how it actually works
The bottom line is that you interact with the data through natural language prompts; the MCP handles all the complicated API calls underneath.
First, subscribe to the Inep Dados Abertos MCP. You may need an INEP API Key if your work requires specific access rights, but public queries usually connect immediately.
Then, prompt your AI client with a request—for example, asking it to list all available educational packages or running a query against a known dataset resource.
The system executes the necessary search or retrieval function and returns clean, structured data directly into your conversation thread.
Who is this actually for?
Academics and policy analysts who are tired of manually downloading, cleaning, and cross-referencing massive government datasets. If your job involves tracking trends in Brazilian education or analyzing exam performance across regions, this is for you.
Pinpointing specific microdata years and variable combinations (e.g., comparing IDEB scores between two states) that aren't immediately visible in summary reports.
Pulling live, verifiable statistics on school infrastructure or exam performance to write an article without relying on outdated public summaries.
Monitoring educational indicators across different regions of Brazil to track the impact of policy changes over time.
What Changes When You Connect
Stop sifting through folders. Use list_packages and search_packages to quickly narrow down the exact dataset you need without guessing names.
Skip manual joins. Running a query with search_datastore_sql lets you filter millions of records using standard SQL syntax, getting targeted results immediately.
No more downloading massive files just to check metadata. Use get_package or get_resource to inspect the structure and find direct download links for specific data components.
The entire INEP catalog is searchable. If you need a resource on 'Censo Escolar' but don't know its exact package name, use search_resources to pinpoint it.
Understand data hierarchy instantly. You can map the relationships between departments using list_organizations and then drill down with get_group.
See it in action
Investigating regional disparities in high school performance
The analyst needs to compare ENEM scores year-over-year across multiple states. They use the MCP to first find all relevant packages using search_packages, then execute a complex SQL query via search_datastore_sql that filters by state code and academic year, delivering a clean comparative table.
Quickly validating data for an article
A journalist needs the most recent school infrastructure counts. They use list_tags to find 'school infrastructure,' then use search_resources to locate the specific CSV file and retrieve its direct download link, bypassing the main portal interface.
Mapping departmental data ownership
A policy analyst needs to know which INEP department (organization) owns the IDEB metrics. They run list_organizations to identify the responsible body and use get_organization for their specific contact details.
Determining data scope for a new project
A researcher needs to know if 'Censo Escolar' has microdata from 2010 to 2023. They use list_groups to see the available thematic groupings, then use get_group to confirm the data scope and variable depth.
The honest tradeoffs
Treating it like a general web search
Asking the agent: 'Tell me about Brazilian education.' This will give you vague marketing fluff, not usable data.
Be specific. Start by listing available packages using list_packages, then use search_datastore with clear criteria like 'microdata 2019' to focus the results.
Downloading everything and cleaning it locally
Manually navigating through multiple INEP sections, downloading dozens of large zip files, and spending days merging them into one usable spreadsheet.
Instead, use search_datastore_sql to query the data directly. You tell the MCP exactly which columns you need (e.g., school code, state, year) and it returns only that filtered subset.
Assuming a dataset is complete
Using get_package and assuming all necessary variables are included. You might miss regional variations or specific filters.
Always check the metadata using get_resource after finding a package. This lets you inspect the full structural information before starting your analysis.
When It Fits, When It Doesn't
Use this MCP if your primary need is deep, structured data access: querying specific fields (via search_datastore_sql), or catalog discovery across massive, organized datasets (using list_packages and get_package). Don't use it if you are just looking for a high-level overview or general facts; those require standard web searching. If your goal is merely to find contact information for INEP departments, start with list_organizations. But remember that the power comes from combining discovery (e.g., using search_packages) and extraction (using search_datastore).
Questions you might have
How do I find out what datasets are available using list_packages? +
Using list_packages gives you a master list of all major educational data sets, like ENEM or IDEB. If you need to focus on one type, follow up by running search_packages with keywords.
What is the difference between search_datastore and search_datastore_sql? +
search_datastore handles simpler text searches within a dataset. If you need to filter data using specific criteria, like 'state equals SP' or 'year greater than 2015,' use search_datastore_sql.
I found a resource ID; how do I get its details? Use get_resource. +
The get_resource tool retrieves the full metadata for that specific data file. This is useful because it shows you structural info, download links, and other key details.
Do I need to use list_organizations first? +
No. You can jump straight into searching or listing packages if you know the general data subject. However, list_organizations helps map out which governmental body is responsible for a specific dataset.
What steps do I take to use my specific Inep API Key when calling get_package? +
The system allows both public and private credentials. To ensure proper access, pass your unique API key in the designated header or parameter field before running any data retrieval tool.
I want to see all available research areas; how do I use list_tags? +
Running list_tags provides a comprehensive index of all metadata tags (like 'IDEB' or 'ENEM'). Use this list first to narrow your scope, guiding you toward the correct dataset package.
How do I get specific details about a Ministry division using get_organization? +
You must identify the organization ID by running list_organizations first. Passing that unique ID to get_organization returns detailed metadata, helping you understand the department's focus.
I don't know the package name; how do I find a resource using search_resources? +
This function searches across all available dataset metadata. It lets you locate specific resources by general keywords (like 'school infrastructure') even if you haven't identified the main parent dataset yet.
Can I query specific data inside a resource without downloading the whole file? +
Yes! You can use the search_datastore_sql tool to run SQL queries directly against the Inep database for resources that support the DataStore API.
How do I find datasets related to a specific topic like 'ENEM'? +
Use the search_packages tool with the query 'ENEM'. It will return all matching datasets, which you can then inspect using get_package.
Is it possible to list all organizations that publish data on the portal? +
Yes, the list_organizations tool retrieves all departments and entities within Inep that maintain open data resources.
We've already built the connector for Inep Dados Abertos. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 12 tools are live and waiting.
You're up and running in seconds.
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.