What can you do with this server?

This MCP server provides AI agents with structured access to U.S. EPA environmental data through the Envirofacts API, integrating multiple EPA databases including FRS (Facility Registry - 800,000+ facilities), TRI (Toxics Release Inventory), SDWIS (Safe Drinking Water Information System), and RCRA (Resource Conservation and Recovery Act). Key Capabilities: * Environmental Summary by Location - Get comprehensive environmental snapshots for any U.S. address, city, or ZIP code within a customizable radius (up to 100 miles), including nearby regulated facilities, chemical releases, water quality violations, hazardous waste sites, and distance-ranked results with summary statistics * Facility Search - Find EPA-regulated facilities by name (partial matching), NAICS code, state, city, or ZIP code with details on programs, locations, coordinates, and industry classifications (up to 1,000 results per query) * Chemical Release Data - Query TRI data by chemical name, CAS number, state, county, or year with comprehensive release aggregations by medium (air, water, land, underground injection), year-over-year trend analysis, and identification of top polluters * Facility Compliance History - Retrieve compliance and enforcement records using FRS Registry ID or program-specific IDs (RCRA Handler ID, TRI Facility ID) with program filtering, violation dates and status, and historical data (up to 20 years) * Health Check - Verify server status, EPA API connectivity, version information, and configuration settings * Geocoding Support - Built-in conversion of addresses, cities, and ZIP codes to geographic coordinates for spatial analysis Features: Parallel API calls for improved performance, robust error handling with retry logic, no API key required (uses public EPA data), distance-based filtering and ranking, and comprehensive data aggregation.

How do I use EPA Envirofacts MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@EPA Envirofacts MCP Server show me environmental data for 100 Main St, Boston, MA" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

EPA Envirofacts MCP Server

MCP Python 3.11+ License: MIT

A Model Context Protocol (MCP) server that provides AI agents with structured access to U.S. EPA environmental data through the Envirofacts API.

Features • Installation • Usage • Configuration • Contributing

Features

Environmental Summary by Location: Get comprehensive environmental data for any U.S. location including:
- Nearby regulated facilities (TRI, RCRA, SDWIS, FRS)
- Chemical release data from Toxics Release Inventory
- Safe Drinking Water Act violations
- Hazardous waste sites
- Distance-based ranking and filtering
Search Facilities: Search for EPA-regulated facilities by name, NAICS code, state, ZIP code, or city
Chemical Release Data: Query TRI chemical releases by chemical name, CAS number, state, county, or year with comprehensive aggregations and optional year-over-year trends
Geocoding Support: Convert addresses, cities, and ZIP codes to coordinates
Robust Error Handling: Retry logic, timeout handling, and graceful degradation
Modular Architecture: Easy to extend with additional EPA data tools
Comprehensive Testing: Unit tests with mocks and integration tests with live API

Installation

Quick Start (Recommended)

Install using uv (fastest method):

# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh

# Clone and install
git clone https://github.com/zachegner/envirofacts-mcp
cd envirofacts-mcp
uv sync

Docker Installation (No Local Setup Required)

Prerequisites:

Docker and Docker Compose

Quick Start:

# Clone the repository
git clone https://github.com/zachegner/envirofacts-mcp
cd envirofacts-mcp

# Build and run with Docker
docker build -t epa-mcp .
docker run -i --rm epa-mcp

Using Docker Compose (Recommended):

# Clone the repository
git clone https://github.com/zachegner/envirofacts-mcp
cd envirofacts-mcp

# Copy environment configuration
cp .env.example .env
# Edit .env with your preferred settings (optional)

# Start the server
docker-compose up mcp-server

# Or run in background
docker-compose up -d mcp-server

Configuration:

Create a .env file from the template:

cp .env.example .env
# Edit .env with your preferred settings

Running Tests with Docker:

# Run unit tests
docker-compose run test

# Run integration tests (requires internet)
docker-compose run test pytest tests/ -v -m integration

Development with Docker:

The docker-compose.yml includes volume mounts for live development:

Source code changes are reflected immediately
No need to rebuild the image for code changes
Use docker-compose up mcp-server for development

Alternative: Traditional Installation

Prerequisites:

Python 3.11 or higher
pip (Python package manager)

Steps:

# Clone the repository
git clone https://github.com/zachegner/envirofacts-mcp
cd envirofacts-mcp

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -e .

Using with Claude Desktop or Other MCP Clients

Add this configuration to your MCP client settings (e.g., claude_desktop_config.json):

With Docker (Recommended for easy setup):

{
  "mcpServers": {
    "epa-envirofacts": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "epa-mcp"
      ]
    }
  }
}

With Docker Compose:

{
  "mcpServers": {
    "epa-envirofacts": {
      "command": "docker-compose",
      "args": [
        "run",
        "--rm",
        "mcp-server"
      ]
    }
  }
}

With uv (requires local Python setup):

{
  "mcpServers": {
    "epa-envirofacts": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/envirofacts-mcp",
        "run",
        "python",
        "server.py"
      ]
    }
  }
}

With traditional installation:

{
  "mcpServers": {
    "epa-envirofacts": {
      "command": "python",
      "args": ["/absolute/path/to/envirofacts-mcp/server.py"]
    }
  }
}

Configuration (Optional)

Create a .env file for custom settings:

cp .env.example .env
# Edit .env with your preferred settings

Configuration

The server can be configured through environment variables or a .env file:

# EPA API Configuration
EPA_API_BASE_URL=https://data.epa.gov/efservice/
REQUEST_TIMEOUT=300
RETRY_ATTEMPTS=3
MAX_RESULTS_PER_QUERY=1000

# Geocoding Configuration
GEOCODING_SERVICE=nominatim
GEOCODING_USER_AGENT=epa-envirofacts-mcp/1.0
GEOCODING_API_KEY=

# Logging Configuration
LOG_LEVEL=INFO

Configuration Options

EPA_API_BASE_URL: Base URL for EPA Envirofacts API (default: https://data.epa.gov/efservice/)
REQUEST_TIMEOUT: Request timeout in seconds (default: 300)
RETRY_ATTEMPTS: Number of retry attempts for failed requests (default: 3)
MAX_RESULTS_PER_QUERY: Maximum results per API query (default: 1000)
GEOCODING_SERVICE: Geocoding service to use (default: nominatim)
GEOCODING_USER_AGENT: User agent string for geocoding requests
LOG_LEVEL: Logging level (DEBUG, INFO, WARNING, ERROR)

Usage

Running the Server

With Docker (Recommended for easy setup)

# Build and run
docker build -t epa-mcp .
docker run -i --rm epa-mcp

# Or with Docker Compose
docker-compose up mcp-server

With uv (requires local Python setup)

uv run python server.py

Traditional Method

# Make sure your virtual environment is activated
source venv/bin/activate  # On Windows: venv\Scripts\activate
python server.py

The server will start and register the available tools. You can then connect to it using an MCP client (like Claude Desktop).

Connecting to Claude Desktop

Open your Claude Desktop configuration file:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
Add the EPA Envirofacts MCP server:

{
  "mcpServers": {
    "epa-envirofacts": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/yourusername/path/to/envirofacts-mcp",
        "run",
        "python",
        "server.py"
      ]
    }
  }
}

Restart Claude Desktop
Look for the 🔌 icon to confirm the server is connected

Available Tools

1. Environmental Summary by Location

Get comprehensive environmental data for any U.S. location.

Parameters:

location (string): Address, city, or ZIP code (e.g., "New York, NY", "10001", "Los Angeles, CA")
radius_miles (float, optional): Search radius in miles (default: 5.0, max: 100.0)

Returns:

Location coordinates and search parameters
Count of facilities by type (TRI, RCRA, SDWIS, FRS)
Top facilities ranked by distance
Water systems and active violations
Chemical release summary with top chemicals
Hazardous waste sites
Summary statistics

Example Usage:

# Get environmental summary for NYC
summary = await get_environmental_summary_by_location("10001", radius_miles=3.0)

print(f"Found {summary.total_facilities} facilities")
print(f"Active water violations: {summary.total_violations}")
print(f"Chemical releases: {summary.chemical_releases.total_releases} pounds")

2. Search Facilities

Search for EPA-regulated facilities using various filters.

Parameters:

facility_name (string, optional): Partial or full facility name (uses contains matching)
naics_code (string, optional): NAICS industry code
state (string, optional): Two-letter state code (e.g., 'NY', 'CA')
zip_code (string, optional): 5-digit ZIP code
city (string, optional): City name
limit (int, optional): Maximum results to return (default: 100, max: 1000)

Returns:

List of facilities with:
- Registry ID and facility name
- Address and location information
- Active EPA programs (TRI, RCRA, etc.)
- Industry codes and descriptions
- Facility status

Example Usage:

# Search by facility name
facilities = await search_facilities(facility_name="Chemical")

# Search by state and city
facilities = await search_facilities(state="CA", city="Los Angeles")

# Search by NAICS code
facilities = await search_facilities(naics_code="325199")

# Search with multiple parameters
facilities = await search_facilities(
    facility_name="Manufacturing",
    state="TX",
    limit=50
)

print(f"Found {len(facilities)} facilities")
for facility in facilities[:3]:
    print(f"{facility.name} - {facility.city}, {facility.state}")

3. Chemical Release Data

Query TRI chemical releases with flexible search parameters and comprehensive aggregations.

Parameters:

chemical_name (string, optional): Chemical name (partial match, e.g., 'benzene')
cas_number (string, optional): CAS Registry Number (exact match, e.g., '71-43-2')
state (string, optional): Two-letter state code (e.g., 'NY', 'CA')
county (string, optional): County name (filtered client-side)
year (int, optional): Reporting year (None for most recent available)
limit (int, optional): Maximum results to return (default: 100, max: 1000)
include_trends (bool, optional): Whether to calculate year-over-year trends (default: False)
trend_years (list, optional): Specific years for trend analysis

Returns:

Search parameters used
Summary statistics (total facilities, chemicals, releases)
Releases by medium (air, water, land, underground injection)
Facilities grouped by facility with all their chemical releases
Chemicals grouped by chemical with all facilities releasing them
Top facilities and chemicals by total releases
Optional year-over-year trends with percentage changes

Example Usage:

# Search by chemical name
data = await get_chemical_release_data(chemical_name="benzene", state="CA")

print(f"Found {data.total_facilities} facilities releasing benzene")
print(f"Total releases: {data.total_releases} pounds")
print(f"Air releases: {data.air_releases} pounds")

# Search by CAS number
data = await get_chemical_release_data(cas_number="71-43-2", year=2022)

# Search with trends
data = await get_chemical_release_data(
    chemical_name="lead", 
    include_trends=True,
    trend_years=[2020, 2021, 2022]
)

if data.trends:
    trend = data.trends[0]
    print(f"Trend direction: {trend.trend_direction}")
    print(f"Percentage change: {trend.percentage_change}%")

4. Facility Compliance History

Get compliance and enforcement history for EPA-regulated facilities.

Parameters:

registry_id (string): FRS Registry ID or program-specific ID (RCRA Handler ID, TRI Facility ID)
program (string, optional): Filter by program ('TRI' or 'RCRA')
years (int, optional): Historical years to include (default: 5, max: 20)

Returns:

Facility information
Compliance records by program
Violations with dates and status
Overall compliance status
Summary statistics

Example Usage:

# By FRS registry ID
compliance = await get_facility_compliance_history("110000012345")

# By program-specific ID with filter
compliance = await get_facility_compliance_history("VAD000012345", program="RCRA")

# With custom timeframe
compliance = await get_facility_compliance_history("110000012345", years=10)

print(f"Overall status: {compliance.overall_status}")
print(f"Total violations: {compliance.total_violations}")
for record in compliance.compliance_records:
    print(f"{record.program}: {record.status}")

5. Health Check

Check system health and EPA API connectivity.

Returns:

Server status and version
EPA API connectivity status
Configuration information

Example Queries

Environmental Summary Queries

# Major cities
await get_environmental_summary_by_location("New York, NY", 5.0)
await get_environmental_summary_by_location("Los Angeles, CA", 5.0)
await get_environmental_summary_by_location("Chicago, IL", 5.0)

# ZIP codes
await get_environmental_summary_by_location("10001", 3.0)  # NYC
await get_environmental_summary_by_location("90001", 3.0)  # LA
await get_environmental_summary_by_location("48502", 2.0)  # Flint, MI

# Full addresses
await get_environmental_summary_by_location("1600 Pennsylvania Avenue NW, Washington, DC", 2.0)

# Different radius sizes
await get_environmental_summary_by_location("Houston, TX", 1.0)   # Small radius
await get_environmental_summary_by_location("Houston, TX", 20.0)  # Large radius

Facility Search Queries

# Search by facility name
await search_facilities(facility_name="Chemical")
await search_facilities(facility_name="Manufacturing")
await search_facilities(facility_name="Power Plant")

# Search by state
await search_facilities(state="CA")
await search_facilities(state="NY")
await search_facilities(state="TX")

# Search by city
await search_facilities(city="Los Angeles")
await search_facilities(city="Houston")
await search_facilities(city="Chicago")

# Search by ZIP code
await search_facilities(zip_code="10001")  # NYC
await search_facilities(zip_code="90210")  # Beverly Hills
await search_facilities(zip_code="60601")  # Chicago

# Search by NAICS code
await search_facilities(naics_code="325199")  # Chemical manufacturing
await search_facilities(naics_code="221112")  # Electric power generation
await search_facilities(naics_code="324110")  # Petroleum refining

# Combined searches
await search_facilities(facility_name="Chemical", state="CA")
await search_facilities(city="Houston", state="TX")
await search_facilities(facility_name="Power", naics_code="221112")

Chemical Release Queries

# Search by chemical name
await get_chemical_release_data(chemical_name="benzene")
await get_chemical_release_data(chemical_name="lead")
await get_chemical_release_data(chemical_name="mercury")

# Search by CAS number
await get_chemical_release_data(cas_number="71-43-2")  # Benzene
await get_chemical_release_data(cas_number="7439-92-1")  # Lead
await get_chemical_release_data(cas_number="7439-97-6")  # Mercury

# Search by state
await get_chemical_release_data(state="CA")
await get_chemical_release_data(state="TX")
await get_chemical_release_data(state="NY")

# Search by chemical and state
await get_chemical_release_data(chemical_name="benzene", state="CA")
await get_chemical_release_data(chemical_name="lead", state="TX")
await get_chemical_release_data(cas_number="71-43-2", state="NY")

# Search by year
await get_chemical_release_data(chemical_name="benzene", year=2022)
await get_chemical_release_data(state="CA", year=2021)

# Search with trends
await get_chemical_release_data(
    chemical_name="benzene",
    include_trends=True,
    trend_years=[2020, 2021, 2022]
)
await get_chemical_release_data(
    state="CA",
    include_trends=True
)

Testing

Unit Tests

Run unit tests with mocked responses:

# With Docker (recommended)
docker-compose run test

# With uv
uv run pytest tests/ -v

# Traditional method
pytest tests/ -v

Integration Tests

Run integration tests with live EPA API calls (slower):

# With Docker
docker-compose run test pytest tests/ -v -m integration

# With uv
uv run pytest tests/ -v -m integration

# Traditional method
pytest tests/ -v -m integration

Test Coverage

Generate test coverage report:

# With Docker
docker-compose run test pytest tests/ --cov=src --cov-report=html

# With uv
uv run pytest tests/ --cov=src --cov-report=html

# Traditional method
pytest tests/ --cov=src --cov-report=html

Test Categories

Unit Tests: Fast tests with mocked dependencies
Integration Tests: Slower tests with live EPA API calls (marked with @pytest.mark.integration)
Slow Tests: Tests that may take longer (marked with @pytest.mark.slow)

Project Structure

envirofacts-mcp/
├── server.py                    # FastMCP server entry point
├── config.py                    # Configuration settings
├── requirements.txt            # Python dependencies
├── .env.example                 # Example environment variables
├── .gitignore                   # Git ignore file
├── README.md                    # This file
├── src/
│   ├── __init__.py
│   ├── client/                  # EPA API clients
│   │   ├── __init__.py
│   │   ├── base.py             # Base client with retry logic
│   │   ├── frs.py              # FRS (Facility Registry) queries
│   │   ├── tri.py              # TRI (Toxics Release) queries
│   │   ├── sdwis.py            # SDWIS (Safe Drinking Water) queries
│   │   ├── rcra.py             # RCRA (Hazardous Waste) queries
│   │   └── compliance.py        # Compliance history queries
│   ├── models/                 # Pydantic data models
│   │   ├── __init__.py
│   │   ├── common.py           # Common models (LocationParams, Coordinates)
│   │   ├── facility.py         # Facility-related models
│   │   ├── releases.py         # Chemical release models
│   │   ├── water.py            # Water violation models
│   │   ├── summary.py          # EnvironmentalSummary response model
│   │   └── compliance.py       # Compliance history models
│   ├── tools/                  # MCP tools
│   │   ├── __init__.py
│   │   ├── location_summary.py # Tool 1: Environmental summary
│   │   ├── search_facilities.py # Tool 2: Search facilities
│   │   └── compliance_history.py # Tool 3: Compliance history
│   └── utils/                  # Utility functions
│       ├── __init__.py
│       ├── geocoding.py        # Geocoding functions
│       ├── distance.py         # Distance calculations
│       └── aggregation.py      # Data aggregation helpers
├── tests/                      # Test suite
│   ├── __init__.py
│   ├── conftest.py            # Pytest fixtures and mocks
│   ├── client/                # Client tests
│   │   ├── test_base.py
│   │   ├── test_frs.py
│   │   ├── test_tri.py
│   │   ├── test_sdwis.py
│   │   └── test_rcra.py
│   ├── tools/                 # Tool tests
│   │   ├── test_location_summary.py
│   │   ├── test_location_summary_integration.py
│   │   ├── test_search_facilities.py
│   │   ├── test_search_facilities_integration.py
│   │   ├── test_compliance_history.py
│   │   └── test_compliance_history_integration.py
│   └── utils/                 # Utility tests
│       ├── test_geocoding.py
│       ├── test_distance.py
│       └── test_aggregation.py
└── epa-mcp-requirements.md    # Requirements document

EPA Data Sources

The server integrates with multiple EPA data systems:

FRS (Facility Registry Service): Master facility database
TRI (Toxics Release Inventory): Chemical release data
SDWIS (Safe Drinking Water Information System): Water quality violations
RCRA (Resource Conservation and Recovery Act): Hazardous waste sites

Error Handling

The server includes comprehensive error handling:

Network Errors: Automatic retry with exponential backoff
API Timeouts: Graceful handling of EPA API 15-minute timeout
Geocoding Failures: Clear error messages with suggestions
Empty Results: Informative messages instead of errors
Partial Failures: Continue with available data, log warnings

Performance

Parallel API Calls: Uses asyncio.gather() for concurrent EPA API requests
Geocoding Cache: In-memory cache to avoid repeated geocoding requests
Rate Limiting: Respects Nominatim's 1 request/second rate limit
Pagination: Limits results to prevent overwhelming responses
Distance Filtering: Efficiently filters facilities by distance

Development

Setting Up Development Environment

# Clone the repository
git clone <repository-url>
cd envirofacts-mcp

# Install with development dependencies
uv sync --all-extras

# Or with pip
pip install -e ".[dev]"

Running Development Server

# With uv
uv run python server.py

# With auto-reload for development
uv run watchfiles "uv run python server.py" src/

Contributing

Fork the repository
Create a feature branch: git checkout -b feature-name
Make your changes and add tests
Run the test suite: uv run pytest tests/ -v
Commit your changes: git commit -am 'Add feature'
Push to the branch: git push origin feature-name
Submit a pull request

Adding New Tools

To add a new EPA data tool:

Create a new tool file in src/tools/
Implement the tool function with proper error handling
Add unit tests in tests/tools/
Add integration tests if needed
Register the tool in server.py
Update documentation

Code Style

Follow PEP 8 style guidelines
Use type hints for all function parameters and return values
Include comprehensive docstrings
Write tests for all new functionality
Use meaningful variable and function names

Troubleshooting

Common Issues

Installation Issues:

Make sure you have Python 3.11 or higher: python --version
If using uv, ensure it's up to date: uv self update
Try clearing uv cache: uv cache clean

Geocoding Failures:

Check internet connectivity
Verify location string format
Try a different location format (ZIP code vs. city name)
Rate limit: Nominatim allows 1 request/second

API Timeouts:

Reduce search radius
Check EPA API status at https://data.epa.gov/efservice/
Increase timeout in configuration

Empty Results:

Try a larger search radius
Verify location is in the United States
Check if area has EPA-regulated facilities

MCP Connection Issues:

Verify the absolute path in your MCP client configuration
Check that the server starts without errors: uv run python server.py
Restart your MCP client (e.g., Claude Desktop)
Check client logs for connection errors

Debug Mode

Enable debug logging:

# With uv
LOG_LEVEL=DEBUG uv run python server.py

# Traditional method
export LOG_LEVEL=DEBUG
python server.py

Logs Location

Server logs: Check console output
Claude Desktop logs:
- macOS: ~/Library/Logs/Claude/mcp*.log
- Windows: %APPDATA%\Claude\logs\mcp*.log

What is MCP?

The Model Context Protocol (MCP) is an open protocol that enables AI assistants like Claude to securely connect to external data sources and tools. This server implements MCP to provide access to EPA environmental data.

Learn more: modelcontextprotocol.io

Available Data Sources

This server provides access to:

FRS (Facility Registry Service): Master facility database with 800,000+ facilities
TRI (Toxics Release Inventory): Chemical release data from industrial facilities
SDWIS (Safe Drinking Water Information System): Water quality and violations data
RCRA (Resource Conservation and Recovery Act): Hazardous waste sites and handlers

All data is sourced from the U.S. Environmental Protection Agency's public Envirofacts API.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

U.S. Environmental Protection Agency for providing the Envirofacts API
Anthropic for the Model Context Protocol
FastMCP framework for MCP server implementation
Geopy library for geocoding functionality
Astral for the uv package manager

Support

For questions, issues, or contributions:

Check the troubleshooting section above
Search existing issues in the repository
Create a new issue with detailed information
Include error messages, configuration, and steps to reproduce

Note: This server provides access to public EPA data. All data is publicly available through the EPA Envirofacts API. No API key is required for basic usage.

Disclaimer: This is an unofficial third-party implementation and is not affiliated with or endorsed by the U.S. Environmental Protection Agency.

EPA Envirofacts MCP Server

Features

Installation

Quick Start (Recommended)

Docker Installation (No Local Setup Required)

Alternative: Traditional Installation

Using with Claude Desktop or Other MCP Clients

Configuration (Optional)

Configuration

Configuration Options

Usage

Running the Server

With Docker (Recommended for easy setup)

With uv (requires local Python setup)

Traditional Method

Connecting to Claude Desktop

Available Tools

1. Environmental Summary by Location

2. Search Facilities

3. Chemical Release Data

4. Facility Compliance History

5. Health Check

Example Queries

Environmental Summary Queries

Facility Search Queries

Chemical Release Queries

Testing

Unit Tests

Integration Tests

Test Coverage

Test Categories

Project Structure

EPA Data Sources

Error Handling

Performance

Development

Setting Up Development Environment

Running Development Server

Contributing

Adding New Tools

Code Style

Troubleshooting

Common Issues

Debug Mode

Logs Location

What is MCP?

Available Data Sources

License

Acknowledgments

Support

Related Projects

Resources

Tools

Appeared in Searches

Latest Blog Posts

MCP directory API