How to Use the AQICN MCP in LangChain

Build multi-step reasoning chains in LangChain using real-time global air quality data from AQICN.

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 LangChain

Create your Vinkius account to connect AQICN 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 AQICN with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain air quality data in LangChain

Feed AQI results directly into your LangChain agents to build automated monitoring pipelines. You can use `get_city_feed` to grab local pollution stats and trigger follow-up actions without manual intervention. Your chains maintain full observability through LangSmith. Every call you make to `get_station_feed` shows up in your traces so you know exactly how the data flows through your logic.

Spatial reasoning for LangChain agents

Define geographic areas for your agents to monitor using `get_map_bounds`. The agent parses the bounding box coordinates and returns a list of active stations in that sector. Combine this with vector stores to cross-reference air quality trends against historical records. Your agent decides the order of operations based on the data returned from `search_stations`.

IP-based location sensing

Trigger location-aware workflows by calling `get_ip_feed` within your LangChain agent. It pulls current pollutant levels for the user's specific network location. This creates a dynamic feedback loop where the agent adapts its reasoning based on the environmental context. You don't need hardcoded coordinates when the MCP Server handles the IP lookup for you.

Setup guide

Set up AQICN 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 AQICN 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({
    "aqicn-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 AQICN 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 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 LangChain

Install the necessary adapters and initialize the MultiServerMCPClient with your endpoint URL. Once connected, pass the tools to your agent constructor to start querying live station data.

Yes, you can chain these tools together so that the output of one call feeds the next. Use the agent's reasoning capabilities to select the right tool based on the initial environment check.

The data returned is structured JSON that fits perfectly into your agent's memory or context window. You can store these observations in your preferred vector database for future retrieval.

You only need to provide an endpoint token when setting up the connection. Vinkius handles the underlying auth so your code stays clean.

This server only processes public air quality metrics and station identifiers. It does not touch your private user data or sensitive local files.

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