Vinkius
PurpleAir logo
Vinkius
Vinkius runs on Vercel AI SDK

How to Use the PurpleAir MCP in Vercel AI SDK

Stream live PM2.5 and temperature readings from PurpleAir sensors directly into your Vercel AI SDK frontend interfaces.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

PurpleAir MCP on Cursor AI Code Editor MCP Client PurpleAir MCP on Claude Desktop App MCP Integration PurpleAir MCP on OpenAI Agents SDK MCP Compatible PurpleAir MCP on Visual Studio Code MCP Extension Client PurpleAir MCP on GitHub Copilot AI Agent MCP Integration PurpleAir MCP on Google Gemini AI MCP Integration PurpleAir MCP on Lovable AI Development MCP Client PurpleAir MCP on Mistral AI Agents MCP Compatible PurpleAir MCP on Amazon AWS Bedrock MCP Support
MCP Servers — Included with Plan
Vinkius runs on Vercel AI SDK

Connect PurpleAir MCP to Vercel AI SDK

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

GDPR Included with Plan

Key Capabilities

Live Air Quality Maps in Vercel AI SDK

Your Vercel AI SDK client uses `get_sensors_by_bounding_box` to pull current air quality metrics for any coordinate box on your map. The tool immediately feeds the coordinate-sorted sensor list into your streaming UI, letting users watch local PM2.5 numbers populate without waiting for a full page reload. By passing these results to your UI components, you bypass the typical slow API fetch cycles. Your frontend renders real-time pollution updates from `get_sensors_near_me` instantly, turning raw geographical sensor arrays into active map markers using this MCP connection.

Fast Time-Series Rendering in React

The `get_sensor_history` tool pulls historical air quality trends directly into your Vercel AI SDK streaming text responses. Your application handles the raw historical arrays to render charts on the fly, showing users how PM2.5 levels changed over the last twenty-four hours. Instead of writing custom backend aggregation layers, you feed the output of `get_sensor_history_csv` directly into your client-side data visualization libraries. This lets your React charts draw historical pollution curves as the AI streams the textual summary.

Immediate Micro-Climate UI Updates

This MCP Server uses `get_sensor_data` to fetch live, specific sensor readings like humidity, VOCs, and PM1.0 for immediate rendering. Your Vercel AI SDK client updates the local state variables the millisecond the sensor responds, preventing UI lag. You can filter these updates using `get_sensors_by_index` to only query the exact monitors your user is watching. Your interface stays lightweight because the client only pulls data for active indices, avoiding unnecessary network overhead.

Setup guide

Set up PurpleAir MCP in Vercel AI SDK

Prerequisites

  • Node.js 18+ and a TypeScript project
  • ai + @modelcontextprotocol/sdk packages
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Install dependencies

    Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).

  2. 2

    Create the Streamable HTTP transport

    Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

  3. 3

    Discover and use tools

    Call mcpClient.tools() to auto-discover all PurpleAir tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.

  4. 4

    Works with any model provider

    Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts
import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent PurpleAir transactions",
});

console.log(text);
await mcpClient.close();

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.

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 Vercel AI SDK

You install the `@ai-sdk/mcp` package and initialize the client using the Vinkius HTTP endpoint. Pass the tools from `get_pm25_sensors` into `streamText` to let your agent output live particulate levels directly to your frontend.
Yes. Use `get_sensor_history` to pull Unix timestamped data arrays, and then parse the response inside your UI components. The SDK streams the text analysis while your charting library renders the parsed historical points.
The server runs inside the Vinkius V8 sandbox, which keeps response times under 200 milliseconds. Your edge functions won't time out because tools like `get_outdoor_sensors` return direct, lightweight payloads.
No. Vinkius manages the PurpleAir API credentials securely on the server side. Your client only needs one Vinkius endpoint token to authorize all calls.
The MCP Server never stores the raw latitude and longitude coordinates sent to `get_sensors_near_me`. All spatial queries pass through an ephemeral, zero-trust V8 sandbox that destroys the session memory immediately after returning the sensor data.

Start using the PurpleAir MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 10 tools

We've already built the connector for PurpleAir. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting. You're up and running in seconds.

Vinkius runs on Claude Claude
Vinkius runs on ChatGPT ChatGPT
Vinkius runs on Cursor Cursor
Vinkius runs on Gemini Gemini
Vinkius runs on Windsurf Windsurf
Vinkius runs on VS Code VS Code
Vinkius runs on JetBrains JetBrains
Vinkius runs on Vercel Vercel
+ other MCP clients

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.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.