How to Use the Minas Gerais (Estado) MCP in LlamaIndex

Q: How do I build a vector index of Minas Gerais (Estado) datasets in LlamaIndex?

You use McpToolSpec to load the Minas Gerais (Estado) MCP Server tools into your LlamaIndex environment. From there, you can run listpackages and load the resulting metadata documents into a VectorStoreIndex for semantic retrieval.

Q: Can LlamaIndex query Minas Gerais (Estado) resources dynamically?

Yes, the FunctionAgent can dynamically invoke searchresources or getresource based on user queries using the MCP adapter. It retrieves the file links directly from the state's portal and uses them to answer specific data questions.

Q: Can I filter my index by state organization?

Yes, you can use getorganization to fetch all datasets belonging to a specific department, then index only those documents. This keeps your local vector store focused on a single state agency's data.

Q: Where does the Minas Gerais dataset metadata go during indexing?

The metadata parsed by tools like getpackage remains entirely within your local LlamaIndex vector store. The MCP Server acts as a read-only bridge to the state's public CKAN portal, meaning no local data or index embeddings are ever shared back to the Brazilian government.

Index Minas Gerais (Estado) open data directly into your LlamaIndex vector stores for hallucination-free public sector RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Minas Gerais (Estado) MCP to LlamaIndex

Create your Vinkius account to connect Minas Gerais (Estado) 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 Minas Gerais (Estado) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect LlamaIndex to the Minas Gerais MCP Server

LlamaIndex doesn't just call the state's API; it indexes the results. When your agent runs `get_package` or `get_resource`, the resulting Minas Gerais (Estado) metadata is ingested directly into your vector store. This lets you build semantic search engines over the state's public catalog. Instead of relying on the LLM's outdated training data, your application queries live state records. You can run `list_packages` to pull the latest datasets and immediately index them, ensuring your RAG system stays current with the state's releases.

Semantic search over state groups and tags

Use LlamaIndex query engines to search through public categories. By combining `list_groups` and `list_tags` with your index, you can map user questions to the exact Minas Gerais (Estado) category. The index acts as a translation layer between natural language and the state's database structure. Your agent can use this semantic map to decide whether to call `search_packages` or target a specific organization using `get_organization`. This prevents broad, wasteful API calls to the state portal.

Ground agent responses in actual state files

Stop your agent from making up Brazilian government statistics. When a user asks about public spending or health data, your LlamaIndex agent uses `search_resources` to locate the actual CSV or PDF files hosted by Minas Gerais (Estado). The agent retrieves the file metadata using `get_resource` and provides the direct download link. This ensures every answer is grounded in verifiable state files rather than AI hallucinations.

Setup guide

Set up Minas Gerais (Estado) 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 Minas Gerais (Estado) 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 Minas Gerais (Estado) tools.",
)
response = await agent.run("List recent Minas Gerais (Estado) 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 Minas Gerais Open Data. 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 Minas Gerais (Estado) 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 Minas Gerais (Estado) MCP in LlamaIndex

You use `McpToolSpec` to load the Minas Gerais (Estado) MCP Server tools into your LlamaIndex environment. From there, you can run `list_packages` and load the resulting metadata documents into a `VectorStoreIndex` for semantic retrieval.

Yes, the `FunctionAgent` can dynamically invoke `search_resources` or `get_resource` based on user queries using the MCP adapter. It retrieves the file links directly from the state's portal and uses them to answer specific data questions.

You should configure your LlamaIndex pipeline with rate-limiting middleware. Since tools like `search_packages` query the state's live CKAN API, adding local delays prevents your indexers from getting blocked by the state's server.

Yes, you can use `get_organization` to fetch all datasets belonging to a specific department, then index only those documents. This keeps your local vector store focused on a single state agency's data.

The metadata parsed by tools like `get_package` remains entirely within your local LlamaIndex vector store. The MCP Server acts as a read-only bridge to the state's public CKAN portal, meaning no local data or index embeddings are ever shared back to the Brazilian government.

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