How to Use the Campinas Open Data MCP in Mastra AI

Q: Does the MCP Client in Mastra AI support human-in-the-loop for Campinas data?

Yes. You can configure requireToolApproval on the MCP Client. When your agent wants to use a tool like getpackage, the workflow will pause and wait for a person to approve the action before it proceeds.

Build resilient, automated data pipelines for Campinas public data using Mastra AI's workflow engine.

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 Mastra AI

Create your Vinkius account to connect Campinas Open Data to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Data Discovery Workflows

Set up a Mastra AI agent to monitor the Campinas data portal on a schedule. Your workflow can run `search_packages` every night, looking for new datasets tagged with 'finance' or 'transport'. When it finds one, it can automatically use `get_package` to pull the details and save them to your database. This is a hands-off way to keep your own systems in sync with public data sources. You define the workflow once, and Mastra's engine runs it for you. It's scheduled, automated data gathering.

Create Conditional Data Pipelines

Mastra AI's real strength is conditional logic. You can build a workflow that tries to find a specific dataset with `search_resources`. If that search comes up empty, your workflow can branch, call `list_tags` to find related terms, and then run a new, broader search. This lets you build smarter agents that don't just fail when something isn't found. They can adapt their strategy based on the results of previous tool calls, making your data pipelines more robust.

Resilient Syncing with this MCP Server

Public data portals can be flaky. Mastra AI's built-in retry logic solves that problem. You can build an agent that uses `list_packages` to get every dataset, then loops through them with `get_package` to fetch all metadata. If a network error or API timeout occurs, Mastra automatically retries the call. Your job doesn't crash. The workflow pauses and tries again, using exponential backoff to avoid hammering the server. This makes the Campinas data MCP server a reliable source for your production workflows.

Setup guide

Set up Campinas Open Data MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Campinas Open Data tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "campinas-open-data-mcp-client",
  servers: {
    "campinas-open-data-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Campinas Open Data Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Campinas Open Data tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Campinas Open Data transactions"
);
console.log(result.text);

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 Mastra AI

You define an agent with a cron trigger in your Mastra workflow configuration. That agent can then use the `search_packages` tool with a date filter to find new datasets published since its last run.

Yes, automatically. Mastra AI has built-in support for retries with exponential backoff. If a call to `get_package` fails due to a temporary network issue, your agent will wait and try again without you writing any extra code.

You just chain the tool calls. For instance, an agent can first call `list_organizations`, pass that output to a step that decides which organization to focus on, and then call `search_packages` filtered by that organization ID. Each step's output can be the next step's input.

Yes. You can configure `requireToolApproval` on the MCP Client. When your agent wants to use a tool like `get_package`, the workflow will pause and wait for a person to approve the action before it proceeds.

Absolutely. The server only processes public data identifiers and metadata; no sensitive information is ever involved. Your agent's connection is authenticated with a unique token, and every operation runs in a separate, sandboxed Vinkius environment.

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