How to Use the PurpleAir MCP in OpenAI Agents SDK

Q: What is the best way to filter sensors in OpenAI Agents SDK?

Use the listsensors tool to query by location type, or use getsensorsbyindex if you have specific sensor IDs stored in your database. This minimizes the payload size returned to your agent.

Monitor hyper-local air quality directly in your OpenAI Agents SDK production pipelines with live PurpleAir data.

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 OpenAI Agents SDK

Create your Vinkius account to connect PurpleAir to OpenAI Agents SDK — 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Real-time PM2.5 tracking with OpenAI Agents SDK

Trigger `get_pm25_sensors` to pull live particulate matter data into your agent's decision loop. Your agents get immediate access to current readings, allowing them to adjust logic based on shifting environmental hazards. This MCP server provides the raw telemetry your agent requires to build health-conscious workflows. By calling `get_sensor_data`, you verify specific pollution levels before the agent executes downstream tasks.

Spatial sensor analysis for OpenAI Agents SDK

Locate specific monitors using `get_sensors_near_me` or `get_sensors_by_bounding_box`. Your agent can now map air quality across specific urban zones without writing custom coordinate logic. These tools return precise latitude and longitude data alongside air metrics. It’s the fastest way to feed location-aware environmental context into your agent's reasoning process.

Historical trend modeling for OpenAI Agents SDK

Access long-term air quality logs using `get_sensor_history` to identify recurring pollution patterns. Your agent can ingest this time-series data to predict future trends or generate compliance reports. Need to perform offline analysis? Use `get_sensor_history_csv` to deliver structured data directly to your agent's processing queue. It keeps your data pipeline clean and avoids manual parsing errors.

Setup guide

Set up PurpleAir MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all PurpleAir tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives PurpleAir tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate PurpleAir tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="PurpleAir Agent",
            instructions="You have access to PurpleAir tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You instantiate an MCPServerStreamableHttp instance pointing to the server endpoint. Pass this object into your agent's configuration, and the SDK will auto-discover all available tools.

Yes. Since the MCP server provides standardized tool outputs, you can wrap your agent's tool execution in try-except blocks to manage network timeouts or missing sensor readings.

The data reflects real-time readings from a global network of sensors. You should always implement your own threshold logic within your agent to handle potential sensor drift or calibration variances.

Use the `list_sensors` tool to query by location type, or use `get_sensors_by_index` if you have specific sensor IDs stored in your database. This minimizes the payload size returned to your agent.

This server only retrieves public air quality sensor telemetry. No private user data or sensitive information is touched or stored by the MCP connection.

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