How to Use the Campinas Open Data MCP in LlamaIndex

Q: Can I use LlamaIndex to create a searchable index of all organizations in the Campinas Open Data portal?

Absolutely. Have your agent call the listorganizations tool and feed the resulting list directly into a LlamaIndex vector store. You can then perform semantic searches over all the city departments and data providers.

Q: How does LlamaIndex handle searching for specific files within the Campinas Open Data datasets?

You'd use the searchresources tool to find the files. LlamaIndex can then index the metadata from the results, letting you ask natural language questions about the files you've already discovered.

Q: What's the process for getting all dataset tags from Campinas Open Data into a LlamaIndex knowledge base?

It's a single tool call. Use the listtags tool and have LlamaIndex ingest the output. This gives your RAG application a complete vocabulary of all topics available in the portal for better query understanding.

Q: Can I get detailed metadata for a specific resource, not just the whole dataset?

Yes, that's what getresource is for. After finding a resource with searchresources, use this tool to fetch its specific details, like file type and creation date, and add them to your index.

Turn Campinas public data into a queryable knowledge base using LlamaIndex and RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Campinas Open Data MCP to LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index City Data on the Fly

LlamaIndex doesn't just call a tool; it ingests the output. When your agent uses `search_packages` to find datasets about 'education', LlamaIndex can automatically index the metadata of those results into a vector store. This builds a local, searchable context for your agent. Subsequent queries get faster and smarter. Your agent searches its own indexed knowledge of Campinas data first, reducing latency and redundant API calls. It's building a memory of the data it has already seen.

Ground Your Answers in Real Data

This is how you stop hallucinations. When a user asks, "What are the latest health datasets?", your LlamaIndex agent queries its vector index built from past `get_package` and `list_packages` calls. It retrieves actual data from the portal to construct the answer. Every response is grounded in facts from the Campinas Open Data portal. Your agent can even cite its sources, making it a trustworthy assistant for anyone doing research on city information. It answers with what it knows, not what it thinks.

Query Your LlamaIndex Agent's History

The index provides a persistent memory. You can ask follow-up questions like, "What were those transportation datasets you found for me yesterday?" The agent retrieves this from its knowledge base without re-running the original `search_packages` query. This makes it perfect for building research bots that learn more about the Campinas data landscape with every query. This MCP server becomes a live data source for your agent's long-term memory, keeping its knowledge base fresh.

Setup guide

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

Absolutely. Have your agent call the `list_organizations` tool and feed the resulting list directly into a LlamaIndex vector store. You can then perform semantic searches over all the city departments and data providers.

You'd use the `search_resources` tool to find the files. LlamaIndex can then index the metadata from the results, letting you ask natural language questions about the files you've already discovered.

It's a single tool call. Use the `list_tags` tool and have LlamaIndex ingest the output. This gives your RAG application a complete vocabulary of all topics available in the portal for better query understanding.

Yes, that's what `get_resource` is for. After finding a resource with `search_resources`, use this tool to fetch its specific details, like file type and creation date, and add them to your index.

The server itself only accesses public data from the Campinas city portal. Your Vinkius endpoint is secured by a unique token, and the connection runs inside a sandboxed environment that's destroyed after use. Your private keys stay on your machine.

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