How to Use the PurpleAir MCP in Mastra AI

Q: How do I require human approval for PurpleAir actions in Mastra AI?

Set requireToolApproval on tools like getsensorhistorycsv when setting up your Mastra agent. The workflow pauses and waits for admin confirmation before running heavy historical data exports.

Build automated air quality workflows in Mastra AI using real-time PurpleAir sensor metrics and automated retries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PurpleAir MCP to Mastra AI

Create your Vinkius account to connect PurpleAir to Mastra AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup PurpleAir with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automated Air Quality Alerts in Mastra AI

The `get_pm25_sensors` tool checks outdoor PM2.5 levels to trigger conditional workflows inside your Mastra AI agent. If particulate levels cross your defined safe threshold, the workflow branches to notify building managers or adjust smart HVAC systems. Mastra uses its built-in retry engine to handle any transient PurpleAir API rate limits automatically. This setup guarantees that your safety-critical checks run reliably without manual intervention when a sensor goes offline.

Multi-Sensor Spatial Audits

This MCP Server feeds `get_sensors_by_bounding_box` data directly into Mastra's multi-step execution graphs. The workflow aggregates readings from dozens of local monitors, filters out outliers, and compiles a clean regional average. If a specific sensor returns anomalous readings, the agent runs `get_sensor_data` on that index to inspect secondary metrics like humidity or VOCs. This multi-step validation prevents false alarms caused by localized dust or sensor malfunctions.

Automatic Historical Air Quality Reporting

Your Mastra AI agent uses `get_sensor_history_csv` to schedule automated daily or weekly pollution reports. The workflow engine runs this query at midnight, converts the CSV data into a clean report format, and sends it to your database. By calling `get_sensor_history`, the agent compares current averages against past baselines. The workflow automatically escalates the report to human review if the running average shows a steady upward trend in local PM2.5.

Setup guide

Set up PurpleAir 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 PurpleAir 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: "purpleair-mcp-client",
  servers: {
    "purpleair-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent PurpleAir 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 PurpleAir. 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 PurpleAir 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 PurpleAir MCP in Mastra AI

Install the Mastra MCP package and instantiate the client with your Vinkius HTTP URL. Spread the tools from `get_outdoor_sensors` directly into your agent's tool array to let it check ambient air quality.

Yes. Mastra's workflow engine uses automatic retries with exponential backoff. If `get_sensor_data` hits a rate limit, the client backs off and retries the request without failing the workflow.

Set `requireToolApproval` on tools like `get_sensor_history_csv` when setting up your Mastra agent. The workflow pauses and waits for admin confirmation before running heavy historical data exports.

You avoid writing boilerplate code for spatial queries and raw JSON parsing. This server exposes ready-to-use tools like `get_sensors_near_me` that your agent understands out of the box.

Your sensor indices and regional query parameters are never stored on disk. The MCP Server processes all API requests in memory within an ephemeral sandbox, ensuring your private sensor coordinates remain completely private.

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