How to Use the EPA AirNow MCP in Google ADK

Q: How do I restrict my Gemini agent to only use the forecast tool?

Pass a toolnames array containing only the forecast tool name when setting up your McpToolset. The agent will ignore the current AQI endpoints.

Feed federal air quality data into Google ADK enterprise agents.

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 Google ADK

Create your Vinkius account to connect EPA AirNow to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query the EPA AirNow MCP Server

Enterprise agents need reliable environmental context. You connect `get_current_aqi_by_zip` to pull real-time air quality index numbers directly from federal monitors. Google ADK lets your Gemini agent take this metric and immediately cross-reference it with your internal BigQuery datasets. You can map employee locations against poor air quality zones in a single reasoning step.

Analyze long-term AQI forecasts

Planning construction or logistics requires looking ahead. The `get_forecast_aqi_by_zip` tool gives your agent the upcoming environmental predictions for any US region. Gemini models hold over a million tokens in context. You can dump weeks of historical operations data alongside these new EPA forecasts, letting the agent spot patterns between past delays and predicted smoke events.

Track specific site coordinates

When a ZIP code is too broad for your facility, `get_current_aqi_by_latlon` targets the exact geographic coordinates. Your agent gets the closest possible sensor reading. You manage exposed capabilities using the tool_names filter in McpToolset. If your agent only needs coordinate data, you restrict access to the other endpoints to keep the execution path strict and predictable.

Setup guide

Set up EPA AirNow MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with EPA AirNow tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="EPA AirNow_agent",
    model="gemini-2.0-flash",
    instruction="You have access to EPA AirNow tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Use McpToolset with StreamableHttpServerParameters pointing to your Vinkius endpoint. Pass that toolset directly to your LlmAgent initialization.

Yes. Your Gemini agent queries the air quality data and can immediately pass those metrics into a custom Vertex AI pipeline for further predictive modeling.

No. The EPA API primarily covers North America. If you pass international coordinates to the tool, the agent will receive empty data arrays.

Pass a tool_names array containing only the forecast tool name when setting up your McpToolset. The agent will ignore the current AQI endpoints.

This MCP Server processes US ZIP codes and geographic coordinates. Vinkius routes these parameters through a zero-trust architecture, authenticating via a single endpoint token without ever logging your specific location queries to disk.

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