Campinas Open Data MCP for AI. Query City Datasets with Natural Conversation
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Campinas Open Data connects your agent directly to Campinas, Brazil's public data portal. Ask questions about city services—like health metrics or education statistics—and retrieve structured metadata for datasets, resources, and organizational sources without leaving your client.
What your AI can do
List groups
Lists all major thematic groupings (like 'Saúde' or 'Educação') used to categorize datasets.
List organizations
Provides a list of every official city department that publishes data through the portal.
List packages
Gives you a comprehensive list of all available dataset names on the platform.
Retrieves full details and structural information for any specific data package.
Gets metadata for individual resources, like a single CSV or PDF file hosted within a larger dataset.
Provides a list of high-level categories (like 'Education' or 'Health') used to organize the data.
Lists all municipal organizations that are contributing public data to the portal.
Retrieves a complete list of every dataset package available on the platform.
Filters and finds packages based on specific keywords, tags, or thematic groups.
Narrows down searches to find individual data files using field names.
Ask an AI about this
Waiting for input…
Campinas Open Data: 8 Tools for Public Records
These tools allow you to systematically discover every layer of public data—from listing groups to inspecting individual file resources.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Campinas Open Data on VinkiusList Groups
Lists all major thematic groupings (like 'Saúde' or 'Educação') used to categorize datasets.
List Organizations
Provides a list of every official city department that publishes data through the...
List Packages
Gives you a comprehensive list of all available dataset names on the platform.
Search Packages
Searches and finds dataset packages based on keywords or criteria you provide.
Get Package
Fetches all the metadata details for a single, specific dataset package.
Search Resources
Narrows down the search to find specific data files using detailed field names.
Get Resource
Retrieves the metadata and structure of an individual data file or resource within a package.
List Tags
Shows every tag used across the portal, allowing for very granular filtering.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Campinas Open Data integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Campinas Open Data, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 8 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Finding Public Data is a Web Crawling Nightmare
Today, figuring out public city data means navigating dozens of portals. You click through departmental tabs, filter by date range, and then manually copy-paste links or download massive ZIP files just to check the metadata structure. It's slow, frustrating, and you're always guessing if the dataset is current.
With this MCP, that whole process vanishes. Your agent handles the navigation. You talk naturally—say, 'Show me all health datasets from the last five years.' The system finds the right packages, checks their metadata, and presents you with structured results without you ever clicking a URL.
Accessing Specific Data Packages
Manual discovery forces you to check multiple places just to compare dataset schemas. You spend time verifying if the 'Education' group data structure matches the 'Health' group data structure, clicking in and out of different tabs.
Now, once your agent finds a potential package name, calling `get_package` confirms every detail—the scope, resource counts, update date. It gives you the full picture immediately, allowing you to write code against reliable schemas.
What your AI can actually do with this
This MCP lets you talk to a massive repository of public records from the city of Campinas using natural language. You don't need to know how to navigate complex government websites; just ask your agent what data you need—say, all datasets related to finance or transport. The system handles the heavy lifting: it finds relevant organizational departments and pulls back metadata for specific files, whether they are PDFs, CSVs, or APIs.
It's really about discovery. You can explore data by tag, browse groups like 'Health,' or check out every department providing records. When you connect this MCP via Vinkius, your agent gets a single point of access to thousands of public resources across the entire catalog, letting you query everything from one place.
019e383b-1514-70c1-bb89-7fc31792f409 
Here's how it actually works
The bottom line is, you talk to it in plain English, and it translates those questions into data queries against the city's official records.
Subscribe to the MCP and provide your Campinas Portal API Key (if required by the data).
Ask your agent a question like: 'List all organizations that track public spending.'
The MCP sends structured requests, and your agent returns the list of departments or dataset metadata you asked for.
Who is this actually for?
This MCP is critical for researchers, journalists, and developers who need reliable access to structured public sector information. It cuts out weeks of manual website navigation by putting all city data discovery into a single chat command.
You use it to systematically gather metadata on datasets, cross-referencing multiple groups (like 'Health' and 'Education') for an urban studies paper.
You connect your agent to inspect API resources and data schemas directly from the command line before writing any transformation code.
You use it to track down public spending records or municipal metrics across different departments by listing organizations and searching for relevant packages.
What Changes When You Connect
Metadata inspection is instant. You get full details on resources and packages using get_package or get_resource, meaning you know the data structure before your code even runs.
You never have to guess where information lives. By running list_organizations, you instantly see which specific city department holds the records you need, cutting down research time dramatically.
Finding relevant data is fast. Instead of clicking through pages, simply ask your agent to use search_packages with keywords like 'finance' or 'transport'.
Explore by topic effortlessly. The list_groups tool lets you browse all city departments' offerings organized into manageable themes.
It handles scale. Whether you need a broad overview of every available dataset using list_packages, or a targeted search with search_resources, the MCP keeps up.
See it in action
Investigating public spending
A journalist needs to track departmental funding. They ask their agent to list all contributing organizations, then use this MCP to search for financial packages across those departments. The system pulls together the metadata and links they need immediately.
Mapping educational resources
An academic needs data on school availability. They ask their agent to list groups, select 'Education,' then use search_packages to find all relevant dataset names like 'Vagas em Creches'. The MCP gives them the full metadata for further analysis.
Debugging a data pipeline
A developer needs to know what fields are available in an existing CSV. They use their agent to get resource metadata via get_resource, confirming column names and formats without downloading or running the actual file.
The honest tradeoffs
Treating all data like one thing
Asking your agent, 'Search for everything about health.' This is too vague; it doesn't tell the system if you mean a whole dataset or just one file.
Be specific. If you need an overview, ask to list_groups and select 'Saúde'. If you know the area, use search_packages with both the group name and the keyword.
Searching without a category
Just typing 'budget data' into the search bar. The system might pull unrelated results because it lacks context.
Always narrow your scope first. Try list_organizations to find the relevant department, then use search_packages filtered by that organization.
Assuming a file is ready
Trying to analyze data immediately after finding a link. You might download a PDF only to realize you don't know its internal structure.
Always run get_resource first on the specific file metadata. This confirms the resource type, format (CSV/PDF), and structural details before you proceed.
When It Fits, When It Doesn't
Use this MCP if your goal is data discovery—you need to find out what public records exist and what their structure is. You'll use search_packages or list_groups when starting broad, and then narrow down using get_package for deep dives. Don't use it if you need real-time transactional data (like current stock prices) or proprietary internal company metrics; this only covers Campinas's public sphere. If you are writing a program that needs to iterate over every single available dataset name, start with list_packages. For inspecting the guts of one specific file, use get_resource.
Questions you might have
How do I find all data provided by a specific city department using list_organizations? +
You use list_organizations first. This tool provides the full roster of contributing entities. Once you identify the correct name, you can then search for that organization's packages using other tools.
What is the difference between list_packages and search_packages? +
list_packages gives you a complete dump of every dataset name available. search_packages lets you filter that massive list instantly by providing keywords or criteria, which is usually faster.
If I find a resource link, what does get_resource do? +
get_resource pulls the specific metadata for an individual file. It tells you if that file is a CSV, what its column names are, and how big it is, without needing to download anything.
Can I search by theme? Should I use list_groups or tags? +
Use list_groups for broad, official categories (like 'Finance'). Use list_tags if you need a more specific, operational keyword that might apply across multiple groups.
When I run get_package, what specific details about the dataset structure do I receive? +
It returns a comprehensive metadata record for that entire package. Beyond the title and description, you'll get critical information like associated tags, groups, the number of contained resources, and the last update date.
If I use search_resources, what is the difference between those results and packages found via search_packages? +
The key difference is scope: A package is a container that holds related data. Using search_resources targets actual files or data points (like a specific CSV), giving you immediate access to the content level.
What happens if I forget to include my API key when running search_packages? +
The MCP will typically reject the request with an authentication error. Remember that while some public data is accessible without a key, restricted or high-volume queries require proper credentials for successful execution.
If I use list_packages and there are thousands of results, should I worry about rate limits? +
Yes, large lists can hit API rate limits. If the initial output is too long to process in one call, structure your subsequent queries iteratively or use pagination parameters if they become available.
How can I search for datasets related to a specific topic like 'Health'? +
You can use the search_packages tool with a query string. For example, searching for 'saude' will return all datasets categorized under health in the Campinas portal.
Can I see which city departments are publishing data? +
Yes! Use the list_organizations tool to get a complete list of all city departments and entities that contribute to the Open Data Portal.
How do I get the download link for a specific data file? +
Use the get_resource tool with the specific Resource ID. It will return the metadata, including the URL to download the file (CSV, PDF, etc.).
We've already built the connector for Campinas Open Data. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 8 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.