How to Use the Campinas Open Data MCP in LangChain

Q: How do I use LangChain to find all datasets from a specific organization in the Campinas Open Data portal?

Have your agent call listorganizations to get the exact organization name first. Then, pass that name as a parameter to the searchpackages tool to get all datasets from that source.

Q: Can my LangChain agent search for specific resources by name within the Campinas Open Data server?

Yes, the searchresources tool is designed for that. Your agent can pass a query directly to it to find individual files, like PDFs of financial reports or specific GeoJSON maps, without needing to know the parent dataset.

Q: What's the best way to explore available data categories from Campinas Open Data with LangChain?

Start by using the listgroups and listtags tools. Your agent can call these to get a full map of the available data themes. This gives it the context to perform more specific and accurate searches later.

Q: How do I get the full metadata for a dataset once my agent finds it?

After searchpackages returns a dataset name, your agent should call getpackage with that name. This tool provides all the details, including the description, update frequency, and associated resources.

Build multi-step agents with LangChain that query Campinas public data, one logical step at a time.

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 LangChain

Create your Vinkius account to connect Campinas Open Data to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Together City Data Queries

Build agents that think in steps. Your LangChain agent can first call `list_organizations` to find a specific city department, then use its output to run a `search_packages` query for that department's datasets. It's a logical sequence, not just a single API call. Because it's a chain, you get full visibility. LangSmith traces show you exactly what happened: which tool your agent chose, the data it passed, and the result it got back. You can debug your agent's reasoning about Campinas data from start to finish.

Let Your LangChain Agent Decide

This isn't about writing rigid scripts. Using a ReAct model, your agent decides what to do next. Give it a vague goal like "find recent financial reports," and it might use `list_tags` to see if 'finance' is a valid tag before using `search_packages`. This turns your agent into a real problem-solver. It intelligently navigates the Campinas data portal, adapting its strategy based on the information it discovers. You're not just calling tools; you're building an agent that can reason about which tool to call.

Mix Campinas Data with Other APIs

LangChain's real strength is connecting different systems. Your agent can find a new public transit dataset using `search_packages`, extract its resource URL with `get_resource`, and then pass that URL to a different tool that sends a Slack message to your data science team. This MCP server becomes the starting point for complex workflows. You can build data pipelines that begin with a query to the Campinas portal and end with an action in your own database, a support ticket, or any other integrated service.

Setup guide

Set up Campinas Open Data MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Campinas Open Data tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "campinas-open-data-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Campinas Open Data transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Have your agent call `list_organizations` to get the exact organization name first. Then, pass that name as a parameter to the `search_packages` tool to get all datasets from that source.

Yes, the `search_resources` tool is designed for that. Your agent can pass a query directly to it to find individual files, like PDFs of financial reports or specific GeoJSON maps, without needing to know the parent dataset.

Start by using the `list_groups` and `list_tags` tools. Your agent can call these to get a full map of the available data themes. This gives it the context to perform more specific and accurate searches later.

After `search_packages` returns a dataset name, your agent should call `get_package` with that name. This tool provides all the details, including the description, update frequency, and associated resources.

Yes. You only manage a single Vinkius endpoint token. Vinkius handles the authentication and runs this MCP Server in an ephemeral, zero-trust sandbox, so your credentials are never exposed when accessing public city data.

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