How to Use the Maranhão Open Data MCP in LlamaIndex

Q: How do I index Maranhão Open Data into LlamaIndex?

Use listpackages to fetch the dataset list, then pass the metadata from getpackage to your LlamaIndex document ingester. This turns the Maranhão registry into searchable vector index nodes.

Q: Can I use LlamaIndex to run SQL queries on Maranhão Open Data?

Yes, you can register the searchdatastoresql tool with your LlamaIndex FunctionAgent. The agent will write SQL queries to fetch Brazilian state data and use the results to answer user prompts.

Q: How does LlamaIndex prevent hallucinations when reading Maranhão Open Data?

By using the searchdatastore tool, LlamaIndex pulls real-time records directly from the Maranhão state registry. The agent uses this live data as its sole context, eliminating the need to guess facts.

Q: What tools does this MCP Server provide to locate specific files in LlamaIndex?

The MCP server provides searchpackages to find datasets and getresource to extract specific file metadata. Your LlamaIndex agent uses these to pinpoint the exact CSV or API endpoint before indexing it.

Index Maranhão Open Data directly into your LlamaIndex vector stores for ground-truth RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Maranhão Open Data MCP to LlamaIndex

Create your Vinkius account to connect Maranhão Open Data 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 Maranhão Open Data with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn Maranhão Open Data into searchable LlamaIndex nodes

The `get_package` tool sends raw metadata from Maranhão's public datasets directly to your LlamaIndex ingestion pipeline. It's fast. The framework parses and chunks these descriptions into searchable vector nodes. By indexing these packages, your RAG application matches user queries to the correct Brazilian government dataset. You bypass manual search entirely, letting the index direct the agent to the exact resource it needs.

Ground LlamaIndex responses using this MCP Server

The `search_datastore_sql` tool gives your LlamaIndex agent the ability to run precise SQL queries over live Maranhão state data. This ensures your synthetic responses are grounded in actual, real-time public records rather than outdated training data. The tool output is converted into document objects that LlamaIndex indexes on the fly. This means your agent can query the database, index the results, and perform semantic search over the returned SQL rows in one go with this MCP Server.

Search Maranhão datastore records in LlamaIndex

The `search_datastore` tool lets your LlamaIndex pipeline query specific resources without writing complex SQL. Your agent passes simple key-value filters to search through Brazilian state records, retrieving only the matching rows. This is ideal for building hybrid search systems. LlamaIndex can combine semantic search from your vector store with exact keyword matches from the Maranhão datastore to give users highly accurate answers.

Setup guide

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

Use `list_packages` to fetch the dataset list, then pass the metadata from `get_package` to your LlamaIndex document ingester. This turns the Maranhão registry into searchable vector index nodes.

Yes, you can register the `search_datastore_sql` tool with your LlamaIndex FunctionAgent. The agent will write SQL queries to fetch Brazilian state data and use the results to answer user prompts.

By using the `search_datastore` tool, LlamaIndex pulls real-time records directly from the Maranhão state registry. The agent uses this live data as its sole context, eliminating the need to guess facts.

The MCP server provides `search_packages` to find datasets and `get_resource` to extract specific file metadata. Your LlamaIndex agent uses these to pinpoint the exact CSV or API endpoint before indexing it.

Your SQL parameters and retrieved state records travel through a secure, zero-trust V8 isolate. Vinkius manages the authentication, ensuring your LlamaIndex pipeline reads Maranhão public data without exposing sensitive credentials.

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