How to Use the EPA AirNow MCP in LlamaIndex

Q: How do I add the EPA AirNow tools to my LlamaIndex agent?

You'll use the McpToolSpec to wrap the MCP client. This exposes the EPA tools from this MCP Server, like getcurrentaqibyzip, in a format LlamaIndex can natively use. Then you just pass the resulting tool list to your agent.

Q: Can I filter which EPA AirNow tools my LlamaIndex agent can use?

Yes. The McpToolSpec lets you specify which tools to expose. You could create an agent that can only fetch forecasts with getforecastaqibyzip, but not current conditions, for example.

Q: How does indexing work for EPA AirNow data in LlamaIndex?

Each time your agent calls a tool like getcurrentaqibylatlon, LlamaIndex can be configured to take the response from the MCP tool call and embed it into your chosen vector database. This makes the specific AQI reading, category, and timestamp available for future semantic searches.

Augment your LlamaIndex knowledge base with live EPA air quality data from an MCP Server.

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 LlamaIndex

Create your Vinkius account to connect EPA AirNow to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Live Air Quality Data

This isn't just another tool for your agent to call. With LlamaIndex, the data returned by `get_current_aqi_by_zip` and `get_forecast_aqi_by_zip` is automatically indexed into a vector store. It turns transient API responses into a persistent, searchable knowledge base. Now you can ask questions about past conditions. "What was the AQI in the Bay Area during last month's fires?" Your RAG application can answer by querying the indexed history of `get_current_aqi_by_latlon` calls, not by guessing.

Build Environment-Aware RAG with LlamaIndex

Combine static documents with live environmental data. For example, you can index your company's outdoor work safety policies alongside the tools from this MCP server. When a user asks, "Is it safe to work outside today in Denver?", your LlamaIndex agent can use `get_current_aqi_by_zip` to get the live AQI, then cross-reference that number with your indexed safety documents to give a precise, context-aware answer.

Query Your Operations with Natural Language

The real power here is turning a stream of API calls into business intelligence. Run `get_forecast_aqi_by_zip` daily for all your warehouse locations. LlamaIndex ingests all of it. A week later, a manager can ask, "Which of our locations had the worst air quality forecasts last week?" The query engine searches the indexed tool outputs and gives a direct answer, grounded in the actual EPA data you collected.

Setup guide

Set up EPA AirNow MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all EPA AirNow MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to EPA AirNow tools.",
)
response = await agent.run("List recent EPA AirNow data")

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 LlamaIndex

You'll use the `McpToolSpec` to wrap the MCP client. This exposes the EPA tools from this MCP Server, like `get_current_aqi_by_zip`, in a format LlamaIndex can natively use. Then you just pass the resulting tool list to your agent.

Yes. The `McpToolSpec` lets you specify which tools to expose. You could create an agent that can only fetch forecasts with `get_forecast_aqi_by_zip`, but not current conditions, for example.

Each time your agent calls a tool like `get_current_aqi_by_latlon`, LlamaIndex can be configured to take the response from the MCP tool call and embed it into your chosen vector database. This makes the specific AQI reading, category, and timestamp available for future semantic searches.

You can do both. The agent can call the tools for immediate, real-time answers. The indexing happens in the background, so you get the benefit of a long-term knowledge base without sacrificing real-time performance.

Your query data—the ZIP code or lat/lon coordinates—is passed through our system to the EPA AirNow API and then discarded. We don't log or retain specific location inputs. The connection itself is secured by your Vinkius account's single endpoint 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