How to Use the EPA AirNow MCP in AutoGen

Q: How do I give my AutoGen agents access to the EPA AirNow tools?

You use the mcpservertools function from the AutoGen extension, pointing it at your Vinkius server URL. This returns a list of tools like getcurrentaqibyzip that you can pass directly into your AssistantAgent configuration.

Let your AutoGen agents debate and decide on actions using live EPA air quality data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EPA AirNow MCP to AutoGen

Create your Vinkius account to connect EPA AirNow 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 EPA AirNow with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enable Multi-Agent Environmental Debate

AutoGen is about conversations between agents, and this server provides the perfect topic for a debate. One agent, a "SafetyOfficer," can use `get_forecast_aqi_by_zip` to flag a potential issue for an outdoor event. A second agent, a "FieldCoordinator," can then challenge that finding. It might argue the forecast is too broad and use `get_current_aqi_by_latlon` to get a precise, real-time reading for the exact venue. The agents then negotiate a final decision based on both pieces of evidence.

Build Consensus-Driven Alert Systems with AutoGen

Don't rely on a single data point. You can create a team of agents that must agree before an action is taken. For instance, an alert for poor air quality is only sent after one agent confirms the forecast with `get_forecast_aqi_by_zip` and another verifies the current situation with `get_current_aqi_by_zip`. This consensus model reduces false positives. The conversation log in AutoGen shows you exactly why the agents made their decision, providing a full audit trail of the data they used from the EPA tools. It's a more careful way to automate critical tasks.

Assign Specialist Roles to Your Agents

Create an agent that specializes in forecasts and only has permission to use the `get_forecast_aqi_by_zip` tool. Create another that's an expert on current conditions, with access to `get_current_aqi_by_latlon` and `get_current_aqi_by_zip`. With this MCP Server, you can easily define these roles. This lets you build more complex and reliable systems where each agent contributes its specific expertise to the group conversation, leading to a better, more nuanced outcome.

Setup guide

Set up EPA AirNow 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 EPA AirNow 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="EPA AirNow_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent EPA AirNow 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="EPA AirNow_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent EPA AirNow 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 EPA. 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 EPA AirNow 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 EPA AirNow MCP in AutoGen

You use the `mcp_server_tools` function from the AutoGen extension, pointing it at your Vinkius server URL. This returns a list of tools like `get_current_aqi_by_zip` that you can pass directly into your `AssistantAgent` configuration.

Absolutely. You can provide the full list of tools to a manager agent, but only give a subordinate agent access to `get_forecast_aqi_by_zip`. This lets you enforce roles and responsibilities within your agent group.

You'd see one agent post a message like, "I've checked the forecast for 90210 with `get_forecast_aqi_by_zip` and the AQI will be 110 tomorrow." Another agent might reply, "That's high. Let's get a current reading with `get_current_aqi_by_zip` to confirm the trend."

It's for different problems. If you need checks and balances or want to combine different expert views before acting, AutoGen's multi-agent debate is ideal. For simple data fetching, a single agent is fine.

The location data your agents use—like a ZIP code for a query—is only used for that single request to the EPA. It is not stored or analyzed by Vinkius. All traffic from your agents runs through a secure, authenticated channel tied to your account's MCP token.

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