How to Use the Inep Dados Abertos MCP in LlamaIndex

Q: How do I index Inep Dados Abertos data into LlamaIndex?

Use searchpackages to locate the target dataset, then pass the resource metadata to your LlamaIndex ingestion pipeline. The framework indexes the metadata so your agent can quickly locate the correct tables.

Q: Can LlamaIndex run SQL queries using the Inep Dados Abertos MCP Server?

Yes, your LlamaIndex agent can use searchdatastoresql to execute direct queries against the school census database. The returned rows are converted into document nodes for semantic search.

Q: How does the Inep Dados Abertos MCP Server prevent hallucinations in LlamaIndex?

By querying live data through searchdatastore, your LlamaIndex agent bases its answers on real government records. It retrieves actual numbers instead of relying on the model's training data.

Q: Can I filter my LlamaIndex vector search using INEP tags?

Yes, your agent can call listtags to fetch official categories and apply them as metadata filters in your vector store. This restricts your search to specific topics like ENEM or Censo Escolar.

Q: Is student data safe when indexing ENEM scores with LlamaIndex?

Yes, all data retrieved via searchdatastore consists of public, aggregate educational statistics compiled by the government. The server does not handle individual student profiles, and all queries are processed securely within your network.

Index raw Brazilian school census and ENEM data directly into your LlamaIndex knowledge base.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Inep Dados Abertos MCP to LlamaIndex

Create your Vinkius account to connect Inep Dados Abertos to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Inep Dados Abertos with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Educational Datasets for RAG

`search_packages` and `get_package` allow your LlamaIndex pipeline to find and ingest educational datasets from the INEP repository. Your agent searches for specific academic years, retrieves the metadata, and prepares the files for indexing. This replaces manual data downloads with an automated ingestion pipeline. Once retrieved, LlamaIndex converts the dataset metadata into searchable document nodes. Your RAG application can then query these nodes to find the exact resource IDs needed for deeper statistical analysis.

Query Live SQL Databases via LlamaIndex MCP Server

`search_datastore_sql` lets your LlamaIndex agent run structured queries against the live Brazilian educational database. The agent translates natural language questions into SQL, pulls the relevant rows, and indexes the results on the fly. That keeps your index updated with live government statistics instead of stale files. By feeding the SQL output from `search_datastore` into your index, you ensure that your RAG system answers queries using factual school metrics. This completely bypasses the hallucination issues common when models guess raw numbers.

Map Resource Schemas for Vector Indexing

`search_resources` and `get_resource` help your LlamaIndex application map the exact structure of INEP's files using this MCP server. Your agent inspects the formats, sizes, and update frequencies to determine the best chunking strategy. High-quality vector embeddings are much easier to generate when you know the exact file structures beforehand. Your agent can also use `list_tags` to tag indexed documents automatically. Adding structured metadata to your vector store allows you to filter search queries by specific themes like higher education or primary school performance.

Setup guide

Set up Inep Dados Abertos MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Inep Dados Abertos MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Inep Dados Abertos tools.",
)
response = await agent.run("List recent Inep Dados Abertos data")

Get your connection token →

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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Inep Dados Abertos now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Inep Dados Abertos MCP in LlamaIndex

Use `search_packages` to locate the target dataset, then pass the resource metadata to your LlamaIndex ingestion pipeline. The framework indexes the metadata so your agent can quickly locate the correct tables.

Yes, your LlamaIndex agent can use `search_datastore_sql` to execute direct queries against the school census database. The returned rows are converted into document nodes for semantic search.

By querying live data through `search_datastore`, your LlamaIndex agent bases its answers on real government records. It retrieves actual numbers instead of relying on the model's training data.

Yes, your agent can call `list_tags` to fetch official categories and apply them as metadata filters in your vector store. This restricts your search to specific topics like ENEM or Censo Escolar.

Yes, all data retrieved via `search_datastore` consists of public, aggregate educational statistics compiled by the government. The server does not handle individual student profiles, and all queries are processed securely within your network.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript