Bring Environmental Data
to OpenAI Agents SDK
Learn how to connect EPA Envirofacts (Environmental Data) to OpenAI Agents SDK and start using 6 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
Compatible with every major AI agent and IDE
What is the EPA Envirofacts (Environmental Data) MCP Server?
Connect to the EPA Envirofacts database to query a wealth of environmental information directly from the United States Environmental Protection Agency.
What you can do
- UV Index Forecasts — Retrieve hourly and daily UV Index forecasts by ZIP code or City/State to monitor solar radiation levels.
- Facility Research — Query the Toxic Release Inventory (TRI) and Superfund (SEMS) databases to find environmental records for specific sites.
- Advanced Data Exploration — Use GraphQL to perform complex queries, aggregations, and cross-table analysis across the EPA's DMAP API.
- Flexible REST Queries — Search any table in the Envirofacts database with custom filters, operators, and pagination.
- Public Data Access — Access official government records on air, water, and waste without complex registration.
How it works
- Subscribe to this server
- No private API key is required for public EPA data access
- Start querying environmental metrics from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Environmental Researchers — quickly pull data from TRI or SEMS for impact analysis and reporting
- Health & Safety Professionals — monitor UV radiation levels to provide accurate safety guidance
- Developers & Data Scientists — integrate official government environmental data into applications via GraphQL or REST
Built-in capabilities (6)
Query EPA Envirofacts using GraphQL
Use program.table format (e.g., tri.tri_facility). Query EPA Envirofacts REST API
Get daily UV Index forecast by City and State
Get daily UV Index forecast by ZIP code
Get hourly UV Index forecast by City and State
Get hourly UV Index forecast by ZIP code
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 6 tools from EPA Envirofacts (Environmental Data) through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries EPA Envirofacts (Environmental Data), another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
EPA Envirofacts (Environmental Data) in OpenAI Agents SDK
EPA Envirofacts (Environmental Data) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect EPA Envirofacts (Environmental Data) to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for EPA Envirofacts (Environmental Data) in OpenAI Agents SDK
The EPA Envirofacts (Environmental Data) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 6 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
EPA Envirofacts (Environmental Data) for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the EPA Envirofacts (Environmental Data) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I check the UV Index for a specific location?
Use the uv_hourly_zip or uv_hourly_city_state tools. Simply provide a 5-digit US ZIP code or the city name and 2-letter state abbreviation to receive the latest hourly forecast data.
Can I search for specific facilities in the EPA database?
Yes! Use the rest_query tool. You can specify tables like 'tri.tri_facility' or 'sems.envirofacts_site' and apply filters using operators like 'equals' or 'contains' to find specific sites and their environmental records.
Does this server support complex data aggregations?
Absolutely. The graphql_query tool allows you to execute custom GraphQL strings to perform advanced data fetching, aggregations, and subqueries across the EPA's DMAP API infrastructure.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
Robin
10 toolsConnect your AI assistant to Robin to seamlessly manage office locations, book meeting rooms, reserve hot desks, and monitor workplace availability directly from chat.

Wrike
6 toolsManage tasks, projects, and folders on Wrike — the most versatile work management platform for teams.

pgvector (Vector Database)
6 toolsRun vector similarity searches, manage embedding tables, and build AI-powered retrieval pipelines — all directly inside your existing PostgreSQL database.

SQL Syntax Validator
1 toolsAudit SQL queries for syntax errors before executing them. Prevent DB crashes and deadlocks with local AST parsing.
