How to Use the AirVisual MCP in OpenAI Agents SDK

Q: How do I connect AirVisual to the OpenAI Agents SDK?

Initialize an MCPServerStreamableHttp object with your Vinkius endpoint URL. Pass that directly into your Agent constructor using the mcpservers list. The SDK automatically discovers all seven environmental tools from the MCP Server.

Q: Can my OpenAI Agents SDK system cache AirVisual data?

Yes, you enable cacheToolsList=True during setup. This prevents the agent from re-fetching the tool schemas for listcountries and liststates on every single execution loop.

Q: Does the agent know which city to query if the user only provides an IP?

It handles that routing natively. The agent executes getnearestcitybyip to resolve the location, then pulls the relevant AQI and weather metrics for that exact spot.

Build production-grade environmental monitoring agents with OpenAI Agents SDK. Get real-time AQI and weather data safely.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AirVisual MCP to OpenAI Agents SDK

Create your Vinkius account to connect AirVisual to OpenAI Agents 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 AirVisual with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Hook up AirVisual to your OpenAI Agents SDK

Your Python agents need reliable environmental data without hallucinating locations. Connecting this MCP Server exposes `get_city_data` directly to your agent's context. You define the guardrails in your OpenAI dashboard while the agent pulls live pollution metrics. Auto-discovery handles the tool mapping for you. When your specialized weather agent needs local conditions, it fires `get_nearest_city_by_ip` and hands the exact AQI values off to your reporting agent.

Drill down into specific monitoring stations

Sometimes city-wide averages hide localized pollution spikes. Your agent can call `list_cities` to map out an area, then iterate through specific sensors using `get_station_data`. The OpenAI tracing dashboard logs every single API call. You see exactly which coordinates your agent passed to `get_nearest_city_by_coords` and how long the MCP endpoint took to respond.

Navigate global hierarchies automatically

Agents often struggle with mismatched geographical names. This integration gives your system the `list_countries` and `list_states` tools to validate locations before querying. Setting `cacheToolsList=True` keeps your agent fast. It learns the valid state codes once, then pulls the actual meteorological data without re-fetching the allowed parameters.

Setup guide

Set up AirVisual 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 AirVisual tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate AirVisual 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="AirVisual Agent",
            instructions="You have access to AirVisual 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 AirVisual. 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 AirVisual 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 AirVisual MCP in OpenAI Agents SDK

Initialize an `MCPServerStreamableHttp` object with your Vinkius endpoint URL. Pass that directly into your Agent constructor using the `mcp_servers` list. The SDK automatically discovers all seven environmental tools from the MCP Server.

Yes, you enable `cacheToolsList=True` during setup. This prevents the agent from re-fetching the tool schemas for `list_countries` and `list_states` on every single execution loop.

It handles that routing natively. The agent executes `get_nearest_city_by_ip` to resolve the location, then pulls the relevant AQI and weather metrics for that exact spot.

The SDK logs every MCP tool execution directly to your OpenAI dashboard. You can inspect the exact payload your agent sent to `get_station_data` and verify the returned pollution metrics.

The V8 Isolate Sandbox destroys all memory the moment your execution finishes. When your agent passes GPS coordinates or IP addresses to find local weather, that data never persists on Vinkius infrastructure.

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