How to Use the EPA Envirofacts (Environmental Data) MCP in AutoGen

Q: What happens if an agent passes an invalid ZIP code to the UV tools?

The uvdailyzip and uvhourlyzip tools return a clear error message directly from the EPA API. Your agents will read this error in the conversation thread, recognize that the input was malformed, and attempt to correct the ZIP code in the next turn of their debate.

Give your AutoGen agents live EPA environmental data to debate toxic releases and UV hazards using actual government metrics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EPA Envirofacts (Environmental Data) MCP to AutoGen

Create your Vinkius account to connect EPA Envirofacts (Environmental Data) 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 Envirofacts (Environmental Data) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query EPA facilities directly from AutoGen agents

The `graphql_query` tool lets your agent pool directly query the EPA Envirofacts database to pull facility-specific data and toxic release inventories. Instead of guessing, one agent can pull a list of active chemical plants in a specific county while a second agent cross-references local demographic data. This forces your multi-agent debates to rely on cold, hard government records rather than generalized summaries. You configure this by passing the server endpoint to your agent constructor. When a debate about localized environmental risk flares up, the agents execute structured GraphQL queries to settle the argument with exact facility coordinates and chemical output metrics.

Cross-examine UV exposure risk across ZIP codes

The `uv_daily_zip` tool pulls direct daily UV index forecasts from the EPA to feed your environmental planning agents. If you are designing a public health campaign, your safety agent can pull hourly forecasts using `uv_hourly_zip` to pinpoint peak danger windows. This replaces broad, useless state-wide averages with localized, hour-by-hour exposure metrics. Your agents use these numbers to negotiate budget allocation between different geographic regions. A performance agent might push for a city-wide campaign, but the data-gathering agent will use these tools to prove that only three specific ZIP codes actually face critical UV thresholds.

Resolve agent conflicts with raw REST table queries

The `rest_query` tool exposes the entire program.table format of the EPA Envirofacts database directly to your AutoGen workflow. This means your agents aren't limited to pre-packaged views; they can query specific tables like tri.tri_facility to extract raw compliance histories. When agents debate whether a local industry poses an active threat, they pull the exact regulatory filings to prove it. This direct access bypasses slow manual research. Your agents run these queries asynchronously during their conversation loop, instantly injecting raw compliance data into their decision-making pipeline.

Setup guide

Set up EPA Envirofacts (Environmental Data) 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 Envirofacts (Environmental Data) 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 Envirofacts (Environmental Data)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent EPA Envirofacts (Environmental Data) 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 Envirofacts (Environmental Data)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent EPA Envirofacts (Environmental Data) 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 Envirofacts. 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 Envirofacts (Environmental Data) 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 Envirofacts (Environmental Data) MCP in AutoGen

You install the MCP extension using pip install -U "autogen-ext[mcp]" and then initialize the server. Pass the server's URL to StreamableHttpServerParams and use mcp_server_tools to generate the tool list. This list goes directly into your AssistantAgent constructor so your agents can call tools like graphql_query during their debates.

Yes, the MCP Server handles concurrent requests from different agents smoothly. If your safety agent calls uv_hourly_city_state while your regulatory agent queries rest_query, the Vinkius managed infrastructure routes both requests without conflicts. This lets your agents debate in real-time using parallel data streams.

The MCP tool adapter in the AutoGen framework automatically converts the tool schemas into the format your agents expect. When an agent invokes graphql_query, the adapter translates the structured JSON response back into the agent's conversation context. This prevents parser errors and keeps the agent debate focused on the actual environmental data.

The uv_daily_zip and uv_hourly_zip tools return a clear error message directly from the EPA API. Your agents will read this error in the conversation thread, recognize that the input was malformed, and attempt to correct the ZIP code in the next turn of their debate.

All queries to the EPA Envirofacts database run inside an isolated, zero-trust V8 sandbox environment. Your search parameters, ZIP codes, and queried facility lists are never stored or logged on our servers. Vinkius acts as an ephemeral proxy, ensuring your operational data remains completely private while your agents pull live environmental metrics.

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