How to Use the AQICN MCP in Mastra AI

Q: Can Mastra AI automatically retry failed AQICN city feed requests?

The framework handles retries natively. If the getcityfeed tool hits a timeout, the workflow engine waits and tries again based on your configured exponential backoff settings.

Q: Does the AQICN MCP server support Mastra AI conditional branching?

Yes, the JSON responses from tools like getipfeed plug directly into your workflow logic. You write standard TypeScript if/else statements based on the returned AQI integers.

Build reliable environmental monitoring workflows in Mastra AI using the AQICN MCP server for conditional air quality alerts.

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 Mastra AI

Create your Vinkius account to connect AQICN 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 AQICN with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Mastra AI Workflows for Pollution Alerts

`get_city_feed` feeds live air quality metrics into your Mastra AI conditional branches. You configure a workflow that checks PM10 levels every hour and only triggers an SMS notification step if the index crosses the unhealthy threshold. Spreading `mcpClient.listTools()` into your Mastra agent gives it instant access to the global sensor network. If a city query fails due to a temporary outage, Mastra's built-in exponential backoff automatically retries the tool call without breaking your pipeline.

Map Bounding Box Analytics

`get_map_bounds` fetches all active air quality stations within specific geographic coordinates through this MCP server. Your automated agent scans an entire region, aggregates the pollution data, and generates a localized report. When paired with `get_station_feed`, the agent loops through the returned station UIDs to pull granular weather and pollutant data. You handle the iteration right inside your TypeScript workflow definitions.

Automate Sensor Discovery

`search_stations` allows your agent to find specific monitoring locations based on text inputs. If a user asks about a neighborhood, the system locates the nearest hardware sensor before attempting to pull the live index. Setting up `get_ip_feed` requires no manual location input. The workflow grabs the network origin, resolves the local air quality, and routes the user down a specific path based on what they are currently breathing.

Setup guide

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

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

const result = await agent.generate(
  "List recent AQICN 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 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 Mastra AI

Install @mastra/mcp and instantiate MCPClient with your Vinkius URL. Call listTools() and spread the results into your agent's tools array. Mastra auto-detects the Streamable HTTP transport.

The framework handles retries natively. If the get_city_feed tool hits a timeout, the workflow engine waits and tries again based on your configured exponential backoff settings.

Use Mastra's requireToolApproval flag. The agent pulls the data via get_station_feed, but pauses and waits for an administrator to approve the actual alert dispatch step.

Yes, the JSON responses from tools like get_ip_feed plug directly into your workflow logic. You write standard TypeScript if/else statements based on the returned AQI integers.

Bounding box coordinates and station UIDs run through an ephemeral zero-trust container. The Vinkius platform destroys the execution environment the moment the get_map_bounds result returns to your workflow engine.

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