How to Use the AQICN MCP in Vercel AI SDK

Q: Can Vercel AI SDK stream AQICN map bounds data to React?

Yes, the AI can call getmapbounds and stream the returned station list to your frontend. You handle the tool call result in your onToolCall callback to update your map state live.

Q: How does Vinkius handle my users' IP addresses when checking AQICN?

When your application triggers getipfeed, the IP string passes through our V8 Isolate Sandbox memory space just long enough to execute the fetch. We do not log the addresses, store the geographic coordinates, or keep the returned pollutant metrics after the connection closes.

Stream real-time global air quality data directly into your React frontends using the AQICN MCP server and Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AQICN MCP to Vercel AI SDK

Create your Vinkius account to connect AQICN to Vercel AI SDK 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 AQICN with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vercel AI SDK Streams AQICN Data

`get_city_feed` pulls live pollutant levels and weather conditions for specific municipalities right into your Vercel AI SDK text streams. Your users watch the PM2.5 and ozone metrics render on screen character by character instead of staring at a spinning loading wheel. Connecting this MCP server via `createMCPClient` means you pass the tool directly into `streamText`. The frontend gets the exact air quality index numbers the moment the HTTP transport resolves the request.

Build IP-Aware Environmental Dashboards

`get_ip_feed` grabs the local air quality index based on the visitor's current network location. You don't have to prompt them for a zip code or rely on browser geolocation APIs to show them what they are breathing right now. Combine that with `get_map_bounds` to populate interactive Next.js map components. The agent grabs all monitoring stations within the viewport coordinates and pipes that data straight into your UI components.

Target Individual Monitoring Sensors

`get_station_feed` queries the exact hardware sensor by its unique ID across the 30,000 available worldwide stations. When a user clicks a specific pin on your frontend, the agent fetches the exact temperature, wind, and pollutant breakdown for that specific block. Finding those sensors happens through `search_stations`. Your AI client matches user queries against the global database, returning the UIDs needed to pull the granular data.

Setup guide

Set up AQICN 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

Install dependencies

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

Discover and use tools

Call mcpClient.tools() to auto-discover all AQICN tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
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 AQICN transactions",
});

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

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 AQICN. 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 AQICN 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 AQICN MCP in Vercel AI SDK

Install @ai-sdk/mcp and initialize with createMCPClient. Point the HTTP transport URL to your Vinkius endpoint. Pass the resulting mcpClient.tools() array into your streamText call.

Yes, the AI can call get_map_bounds and stream the returned station list to your frontend. You handle the tool call result in your onToolCall callback to update your map state live.

Vercel AI SDK surfaces the tool call error directly to your application layer. You should catch this in your route handler and either show a fallback UI or ask the user to try their request again later.

The HTTP transport layer works perfectly on the Edge. You just need to ensure you call mcpClient.close() after your generation finishes to prevent hanging connections.

When your application triggers get_ip_feed, the IP string passes through our V8 Isolate Sandbox memory space just long enough to execute the fetch. We do not log the addresses, store the geographic coordinates, or keep the returned pollutant metrics after the connection closes.

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