# EPA Enforcement Intelligence MCP — ECHO Database (`andrew_avina/epa-intelligence-mcp`) Actor Search 500,000+ EPA-regulated facility records for environmental violations, inspections, toxic releases, and compliance status — directly from your AI assistant. - **URL**: https://apify.com/andrew\_avina/epa-intelligence-mcp.md - **Developed by:** [Andrew Avina](https://apify.com/andrew_avina) (community) - **Categories:** MCP servers, Business - **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing $3.00 / 1,000 result item returneds This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## EPA Enforcement Intelligence MCP Search 500,000+ EPA-regulated facility records for environmental violations, inspections, toxic releases, and compliance status — directly from your AI assistant. ### Overview This Apify Actor exposes EPA Enforcement and Compliance History Online (ECHO) data through a Model Context Protocol (MCP) server, making it trivially easy to integrate real-time environmental compliance data into Claude, GPT-4, Cursor, or any MCP-compatible AI workflow. The actor wraps three EPA ECHO REST endpoints (Clean Water Act, Hazardous Waste, and Combined multi-program) and normalizes their output into a consistent schema covering: - Clean Water Act (CWA) discharge violations - Hazardous waste compliance (RCRA — Resource Conservation and Recovery Act) - Clean Air Act (CAA) formal enforcement actions - Toxic Release Inventory (TRI) reporter status and annual release amounts - EPA inspection counts and active violation flags No API key is required. All data is sourced from EPA's public ECHO system, which is updated daily. --- ### Use Cases #### Environmental Due Diligence (M&A) Screen acquisition targets for environmental liability before closing. Search by company name + state, check CWA violation counts and TRI releases, and flag facilities with active enforcement actions — all in a single AI conversation. #### EHS Compliance Teams Monitor competitors or supply chain partners for emerging enforcement patterns. Use NAICS code filtering to identify industry-wide trends. #### Real Estate & Lending Screen commercial real estate or loan collateral for environmental risk using facility name and address inputs. #### Legal & Consulting Quickly surface EPA enforcement history for litigation support, regulatory consulting, or CERCLA/Superfund preliminary assessments. #### Regulatory Journalists Identify the worst violators in a state or industry in seconds. TRI release data (pounds of toxic chemicals released per year) is particularly useful for investigative reporting. --- ### MCP Tools #### `search_facilities` Search EPA ECHO facilities by name, state, NAICS code, and violation status. **Arguments:** | Parameter | Type | Description | |-----------|------|-------------| | `facility_name` | string | Facility or company name (partial match). Example: `"Exxon"`, `"DuPont"` | | `state` | string | 2-letter state abbreviation. Example: `"TX"`, `"CA"` | | `naics_code` | string | 6-digit NAICS code. Example: `"325110"` (Petrochemical Mfg) | | `has_violations` | boolean | If `true`, only return facilities with active violations | | `program` | string | `"cwa"` (Clean Water Act), `"rcra"` (Hazardous Waste), `"all"` (Combined) | | `limit` | integer | Max results (default 25, max 100) | **Example query:** ```json { "name": "search_facilities", "arguments": { "facility_name": "Exxon", "state": "TX", "has_violations": true, "program": "cwa", "limit": 10 } } ```` **Example response record:** ```json { "facility_name": "ExxonMobil Baytown Complex", "registry_id": "110000493620", "city": "Baytown", "state": "TX", "zip": "77522", "naics_code": "324110", "cwa_violations": 3, "caa_violations": 0, "inspections": 12, "tri_reporter": "Y", "tri_releases_lbs": 247000.0, "source": "epa.gov/echo" } ``` *** #### `get_facility_compliance` Get detailed compliance history for a specific facility using its EPA Registry ID. **Arguments:** | Parameter | Type | Description | |-----------|------|-------------| | `registry_id` | string | 12-digit EPA Registry ID (from `search_facilities` results) | **Example query:** ```json { "name": "get_facility_compliance", "arguments": { "registry_id": "110000493620" } } ``` *** #### `search_violations` Find all facilities with active violations in a specific state or city. Returns facilities ranked by violation severity. **Arguments:** | Parameter | Type | Description | |-----------|------|-------------| | `state` | string | 2-letter state abbreviation | | `city` | string | City name (optional) | | `violation_type` | string | `"cwa"`, `"rcra"`, or `"caa"` | | `limit` | integer | Max results (default 25, max 100) | **Example query:** ```json { "name": "search_violations", "arguments": { "state": "WV", "violation_type": "cwa", "limit": 20 } } ``` *** ### Output Schema Every record pushed to the Apify dataset has these fields: | Field | Type | Description | |-------|------|-------------| | `facility_name` | string | Registered facility name in EPA ECHO | | `registry_id` | string | EPA Facility Registry Service (FRS) ID | | `city` | string | Facility city | | `state` | string | 2-letter state abbreviation | | `zip` | string | Facility ZIP code | | `naics_code` | string | Primary NAICS industry code | | `sic_codes` | string | Legacy SIC codes (pipe-delimited) | | `cwa_violations` | integer | Number of Clean Water Act violations in last 3 years | | `caa_violations` | integer | Number of Clean Air Act formal enforcement actions | | `inspections` | integer | Total EPA inspections on record | | `tri_reporter` | string | `"Y"` if facility files TRI reports | | `tri_releases_lbs` | float | Annual toxic releases in pounds (from TRI) | | `source` | string | Always `"epa.gov/echo"` | On error, records include a `_meta` object: ```json { "_meta": { "error": "ECHO API timeout after 30s", "fallback_tried": true } } ``` *** ### Input Parameters | Parameter | Type | Default | Description | |-----------|------|---------|-------------| | `facility_name` | string | `""` | Facility name to search | | `state` | string | `""` | 2-letter state filter | | `naics_code` | string | `""` | NAICS code filter | | `has_violations` | boolean | `false` | Active violations only | | `program` | string | `"all"` | EPA program (all/cwa/rcra) | | `limit` | integer | `25` | Max results (1–100) | | `serveMcp` | boolean | `false` | Enable MCP server mode | *** ### Modes of Operation #### Batch Mode (default) Run the actor with input parameters. It fetches facilities from EPA ECHO, normalizes the results, and pushes them to the Apify dataset. The actor exits when complete. **Best for:** One-time data collection, scheduled monitoring, integration with Apify datasets. #### MCP Server Mode (`serveMcp: true`) The actor starts an HTTP server on port 4321 and runs indefinitely. AI clients connect to it using the MCP protocol. **Best for:** Real-time AI assistant integration (Claude Desktop, Cursor, Continue.dev, etc.). **MCP endpoint URLs (when running):** - `GET http://:4321/mcp/tools` — list available tools - `POST http://:4321/mcp/call` — call a tool - `GET http://:4321/health` — health check *** ### Data Source **EPA Enforcement and Compliance History Online (ECHO)** - URL: https://echo.epa.gov - API docs: https://echo.epa.gov/tools/web-services - Update frequency: Daily - Auth required: None - Coverage: All EPA-regulated facilities in the United States - Programs: CWA (NPDES), RCRA, CAA, TRI, SDWA, and more The three ECHO REST endpoints used: 1. `echodata.epa.gov/echo/cwa_rest_services.get_facilities` — Clean Water Act 2. `echodata.epa.gov/echo/rcra_rest_services.get_facilities` — Hazardous Waste 3. `echodata.epa.gov/echo/combined_data.get_facilities` — All programs *** ### Regulatory Programs Explained #### Clean Water Act (CWA) Governs discharge of pollutants into navigable waters. NPDES (National Pollutant Discharge Elimination System) permits are required for industrial discharges. Violations are tracked as Significant Non-Compliance (SNC) events. **Key ECHO field:** `DrCWVio` — number of SNC quarters in the past 3 years. #### Resource Conservation and Recovery Act (RCRA) Governs generation, treatment, storage, and disposal of hazardous waste. Violations can result from improper labeling, storage beyond 90-day limits, missing manifests, or unauthorized disposal. **Key ECHO field:** `DrRCRAVio` — RCRA violations in past 3 years. #### Clean Air Act (CAA) Governs air emissions from stationary and mobile sources. Formal enforcement actions include compliance orders, administrative penalties, and judicial referrals. **Key ECHO field:** `DrCAAAcc` — CAA formal actions. #### Toxic Release Inventory (TRI) Facilities above certain thresholds must annually report releases of ~650 listed chemicals. TRI data is widely used by communities, investors, and researchers. **Key ECHO field:** `TRIReleasesLbs` — total pounds released per year. *** ### Example AI Prompts Once connected via MCP, you can ask your AI assistant: - *"Search EPA ECHO for Chevron facilities in California with Clean Water Act violations"* - *"Show me all hazardous waste violators in West Virginia"* - *"What are the TRI releases for ExxonMobil's Baytown complex?"* - *"Find petrochemical facilities (NAICS 325110) in Texas with active violations"* - *"Get the full compliance history for EPA registry ID 110000493620"* *** ### NAICS Codes for Environmental Screening Common high-risk industries to filter: | NAICS | Industry | |-------|----------| | 211120 | Crude Petroleum Extraction | | 221112 | Fossil Fuel Electric Power Generation | | 324110 | Petroleum Refineries | | 325110 | Petrochemical Manufacturing | | 325180 | Other Basic Inorganic Chemical Mfg | | 331110 | Iron & Steel Mills | | 332710 | Machine Shops | | 322110 | Pulp Mills | | 562211 | Hazardous Waste Treatment & Disposal | | 486110 | Pipeline Transportation of Crude Oil | *** ### Error Handling The actor never crashes. On any API failure, results include a `_meta` object: ```python {"_meta": {"error": "description", "fallback_tried": True}} ``` Common errors and their causes: - `"ECHO API timeout after 30s"` — EPA servers are temporarily slow; retry the query - `"API returned HTTP 429"` — Rate limited; wait 60 seconds and retry - `"No results found"` — Valid response but no facilities match your criteria - `"No facility found for registry_id=X"` — The registry ID does not exist in ECHO *** ### Technical Details - **Language:** Python 3.11 - **Runtime:** Apify Actor SDK v2 - **HTTP client:** httpx (async, with 30s timeout) - **MCP server:** Pure asyncio TCP server (no external frameworks) - **Port:** 4321 (MCP server mode) - **Memory footprint:** ~64 MB typical *** ### License Data is sourced from EPA ECHO, which is a US federal government public database. Data is in the public domain (17 U.S.C. § 105). Actor code is proprietary. *** ### Support Built and maintained as part of the SECC (Sovereign Executive Command Center) intelligence platform. For issues, feature requests, or data quality questions, open an issue in the Apify store or contact the actor author. # Actor input Schema ## `facility_name` (type: `string`): Facility or company name to search (partial match OK). Examples: 'Exxon', 'DuPont', 'Chevron', 'US Steel'. Leave blank to search by state or NAICS only. ## `state` (type: `string`): 2-letter US state abbreviation to filter results. Examples: 'TX', 'CA', 'WV', 'OH', 'LA'. Leave blank to search all states. ## `naics_code` (type: `string`): 6-digit North American Industry Classification System code. Examples: '325110' (Petrochemical Mfg), '331110' (Iron & Steel Mills), '211120' (Crude Petroleum Extraction), '322110' (Pulp Mills). ## `has_violations` (type: `boolean`): When enabled, only return facilities with active violations (p\_act=Y in EPA ECHO). Use this to focus on non-compliant facilities. ## `program` (type: `string`): Which EPA regulatory program to query. 'cwa' = Clean Water Act (NPDES permits, discharge violations). 'rcra' = Resource Conservation and Recovery Act (hazardous waste). 'all' = Combined multi-program search across CWA, CAA, RCRA, TRI, and others. ## `limit` (type: `integer`): Maximum number of facilities to return (max 100 per the ECHO API). Default is 25. ## `serveMcp` (type: `boolean`): When enabled, starts an MCP-compatible HTTP server on port 4321. Use this to connect Claude Desktop, Cursor, or any MCP client directly to live EPA data. The actor will run continuously until stopped. In this mode, the actor provides 3 tools: search\_facilities, get\_facility\_compliance, and search\_violations. ## Actor input object example ```json { "facility_name": "", "state": "", "naics_code": "", "has_violations": false, "program": "all", "limit": 25, "serveMcp": false } ``` # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = {}; // Run the Actor and wait for it to finish const run = await client.actor("andrew_avina/epa-intelligence-mcp").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = {} # Run the Actor and wait for it to finish run = client.actor("andrew_avina/epa-intelligence-mcp").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{}' | apify call andrew_avina/epa-intelligence-mcp --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=andrew_avina/epa-intelligence-mcp", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "EPA Enforcement Intelligence MCP — ECHO Database", "description": "Search 500,000+ EPA-regulated facility records for environmental violations, inspections, toxic releases, and compliance status — directly from your AI assistant.", "version": "0.1", "x-build-id": "voRocaMM4ZRZiWNAo" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/andrew_avina~epa-intelligence-mcp/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-andrew_avina-epa-intelligence-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/andrew_avina~epa-intelligence-mcp/runs": { "post": { "operationId": "runs-sync-andrew_avina-epa-intelligence-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/andrew_avina~epa-intelligence-mcp/run-sync": { "post": { "operationId": "run-sync-andrew_avina-epa-intelligence-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "facility_name": { "title": "Facility Name", "type": "string", "description": "Facility or company name to search (partial match OK). Examples: 'Exxon', 'DuPont', 'Chevron', 'US Steel'. Leave blank to search by state or NAICS only.", "default": "" }, "state": { "title": "State", "type": "string", "description": "2-letter US state abbreviation to filter results. Examples: 'TX', 'CA', 'WV', 'OH', 'LA'. Leave blank to search all states.", "default": "" }, "naics_code": { "title": "NAICS Code", "type": "string", "description": "6-digit North American Industry Classification System code. Examples: '325110' (Petrochemical Mfg), '331110' (Iron & Steel Mills), '211120' (Crude Petroleum Extraction), '322110' (Pulp Mills).", "default": "" }, "has_violations": { "title": "Active Violations Only", "type": "boolean", "description": "When enabled, only return facilities with active violations (p_act=Y in EPA ECHO). Use this to focus on non-compliant facilities.", "default": false }, "program": { "title": "Regulatory Program", "enum": [ "all", "cwa", "rcra" ], "type": "string", "description": "Which EPA regulatory program to query. 'cwa' = Clean Water Act (NPDES permits, discharge violations). 'rcra' = Resource Conservation and Recovery Act (hazardous waste). 'all' = Combined multi-program search across CWA, CAA, RCRA, TRI, and others.", "default": "all" }, "limit": { "title": "Result Limit", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum number of facilities to return (max 100 per the ECHO API). Default is 25.", "default": 25 }, "serveMcp": { "title": "MCP Server Mode", "type": "boolean", "description": "When enabled, starts an MCP-compatible HTTP server on port 4321. Use this to connect Claude Desktop, Cursor, or any MCP client directly to live EPA data. The actor will run continuously until stopped. In this mode, the actor provides 3 tools: search_facilities, get_facility_compliance, and search_violations.", "default": false } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```