How to Use the IQAir MCP in LangChain

Stop guessing. Give your LangChain agents real-time IQAir environmental data to build smart, multi-step pollution monitoring runs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IQAir MCP to LangChain

Create your Vinkius account to connect IQAir to LangChain 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 IQAir with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain IQAir lookup tools into environmental workflows

The `get_city_air_quality` tool lets your agent pull real-time pollution metrics for any target city in your LangChain runs. You chain this output directly to the next step, letting your agent decide whether to pull regional baselines or trigger warning alerts. By using `list_supported_cities` alongside `list_supported_states`, you build a strict validation step. Your agent checks if a city exists before firing off heavy API calls, saving you from failed runs and wasted tokens.

Debug LangChain MCP Server loops with LangSmith

The `get_nearest_city_air_quality` tool pulls local air metrics based on the user's IP address. When your LangChain agent executes this tool, LangSmith captures the exact coordinates used and the resulting payload. This makes debugging location-based runs incredibly fast. You see exactly when the agent calls `check_api_status` to verify the endpoint before running the main query. Every hop, latency spike, and token count is laid bare in your tracing dashboard.

Ground LangChain decisions in real-world IQAir data

The `list_supported_countries` tool provides the foundational geographic scope your LangChain agent needs to navigate global air indexes. Instead of hardcoding regions, your agent queries this tool first to build dynamic search paths. This means your agent doesn't hallucinate region names when running complex, multi-step reasoning chains. It checks the live endpoint, gets the valid list, and executes the next step with perfect accuracy.

Setup guide

Set up IQAir MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes IQAir tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "iqair-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent IQAir transactions"
    })
    print(result["messages"][-1].content)

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 IQAir. 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 IQAir 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 IQAir MCP in LangChain

Install the langchain-mcp-adapters package and initialize the MultiServerMCPClient with your Vinkius endpoint. Call get_tools to fetch the IQAir tools and pass them directly to your agent constructor.

Yes, your agent can catch errors by chaining lookup tools. If a query fails, the agent calls `list_supported_states` and `list_supported_cities` to find a valid alternative and retry the run.

LangSmith traces every single tool execution in real-time. You see exactly how long `get_city_air_quality` takes to return data, letting you optimize your chain's performance.

This tool lets your agent verify the external API is up before starting a complex chain. If the check fails, your system can gracefully halt or switch to cached data.

Vinkius runs the IQAir MCP server in a secure, ephemeral sandbox that processes IP and coordinate queries on the fly. No location data or IP addresses are stored or logged after the tool returns the air quality metrics to your LangChain agent.

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