How to Use the AirVisual MCP in LangChain

Q: How do I connect the AirVisual MCP Server to LangChain?

Install langchain-mcp-adapters and langgraph. Pass your Vinkius HTTP endpoint into MultiServerMCPClient to expose the tools.

Q: Can LangChain agents chain AirVisual weather requests?

Yes. An agent might grab coordinates, pass them to getnearestcitybycoords, and feed that AQI data into a separate notification tool. Everything flows automatically.

Build multi-step reasoning pipelines that pull live global air quality data directly into your LangChain agents.

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 LangChain

Create your Vinkius account to connect AirVisual 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 AirVisual with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain AirVisual MCP Server Data

AirVisual feeds real-time pollution metrics into your ReAct agents. You build chains where `get_city_data` grabs the current AQI for Paris and passes those numbers straight into a localized health alert generator. The output from one tool call instantly becomes the input for the next step. If the agent needs to find a specific monitoring site first, it runs `list_cities` followed by `get_station_data` before making any formatting decisions.

Trace Environmental Pipelines

LangSmith tracks exactly how your agent navigates the global weather database. You see the exact tokens spent when the system calls `list_countries` to build a regional report. Latency metrics show up on your dashboard the second a tool executes. When your agent runs `get_nearest_city_by_ip` to locate a user, you know exactly how long that API round-trip took.

Build Location-Aware Agents

Your agent determines which tool to call based on the data it holds. Handing it raw GPS coordinates triggers `get_nearest_city_by_coords` automatically. No manual routing is required. The agent looks at intermediate results from `list_states` and decides on its own if it needs deeper station-level data to complete the prompt.

Setup guide

Set up AirVisual 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 AirVisual 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({
    "airvisual-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 AirVisual 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 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 LangChain

Install `langchain-mcp-adapters` and `langgraph`. Pass your Vinkius HTTP endpoint into `MultiServerMCPClient` to expose the tools.

Yes. An agent might grab coordinates, pass them to `get_nearest_city_by_coords`, and feed that AQI data into a separate notification tool. Everything flows automatically.

Every single call gets logged. You track latency and token usage for operations like `get_station_data` right in your LangSmith dashboard.

The ReAct framework reads the tool descriptions provided by the MCP protocol. If the prompt asks for pollution levels by IP, the agent selects the matching tool.

The server processes IPs and GPS coordinates strictly to locate the nearest weather station. Vinkius runs this MCP connection inside an ephemeral V8 sandbox, discarding the location markers immediately after returning the AQI data.

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