How to Use the IQAir MCP in AutoGen

Q: How do I register IQAir tools with my AutoGen agents?

Install autogen-extmcp and use the mcpservertools adapter with your Vinkius URL. Pass the resulting tool list directly to your AssistantAgent constructor.

Q: Can AutoGen agents collaborate on IQAir geographic lookups?

Yes, one agent can call listsupportedstates to find a region, while another agent uses that output to call listsupportedcities and compile the final report.

Let your AutoGen agents debate and verify real-time IQAir pollution metrics before making critical environmental decisions.

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 AutoGen

Create your Vinkius account to connect IQAir to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve environmental debates with live IQAir data

The `get_city_air_quality` tool serves as the ground truth when your AutoGen agents debate local air conditions. A health agent and a safety agent can query this tool to get real-time pollution metrics, then negotiate the best response based on raw numbers. This eliminates guesswork during agent conversations. Instead of arguing over static or outdated figures, both agents access the same live data to reach a consensus.

Verify local air metrics across agent roles

The `get_nearest_city_air_quality` tool allows your AutoGen agents to automatically detect the local environment based on the client's connection point. One agent pulls the local metrics, while a second agent analyzes the weather data to verify the findings. They coordinate this check without manual intervention. If the data looks anomalous, they call `check_api_status` to ensure the feed is reliable before confirming their decision.

Coordinate regional search paths using the AutoGen MCP Server

The `list_supported_countries` tool provides the geographic boundaries for your multi-agent planning sessions. A coordinator agent queries this list to assign specific countries to sub-agents for deeper analysis. Those sub-agents then run `list_supported_states` and `list_supported_cities` to map out their assigned regions. This structured delegation keeps your multi-agent conversation organized and highly efficient.

Setup guide

Set up IQAir MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes IQAir tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="IQAir_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent IQAir data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="IQAir_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent IQAir data")
    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 AutoGen

Install autogen-ext[mcp] and use the mcp_server_tools adapter with your Vinkius URL. Pass the resulting tool list directly to your AssistantAgent constructor.

Yes, one agent can call `list_supported_states` to find a region, while another agent uses that output to call `list_supported_cities` and compile the final report.

The agents debate the results. A verification agent can run `check_api_status` or cross-reference `get_city_air_quality` with surrounding cities to resolve anomalies.

It allows planning agents to segment their search space. Instead of searching blindly, they fetch valid states first to distribute the workload among execution agents.

Vinkius isolates all tool executions on this MCP Server within an ephemeral, zero-trust container. Your IP-derived coordinates and city names are never stored, logged, or exposed to external networks after the tools execute.

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