# OSHA Enforcement Intelligence MCP — 6M+ Inspection Records (`andrew_avina/osha-intelligence-mcp`) Actor Search millions of OSHA workplace safety inspections and violation records directly from your AI assistant. Query by company, state, industry code, date range, and inspection type — with full penalty history. - **URL**: https://apify.com/andrew\_avina/osha-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 ## OSHA Enforcement Intelligence MCP Search millions of OSHA workplace safety inspections and violation records directly from your AI assistant. Query by company, state, industry code, date range, and inspection type — with full penalty history. ### Overview This Apify Actor exposes OSHA enforcement data from the Department of Labor (DOL) Enforcement Data API through a Model Context Protocol (MCP) server. It enables AI assistants (Claude, GPT-4, Cursor, Continue.dev) to answer real-time questions about workplace safety enforcement history across all US industries. The actor connects to the DOL's public `enforcedata.dol.gov` API, normalizes response data into a consistent schema, and handles graceful fallbacks when the API is temporarily unavailable. Every failure path returns a structured `_meta` error record — the actor never crashes. --- ### Use Cases #### EHS Compliance Teams Screen competitors and industry peers for OSHA enforcement patterns. Identify recurring violation types in your sector and proactively address them before OSHA comes to you. #### M&A Due Diligence Before acquiring a manufacturing, logistics, or food processing company, screen all known facilities for OSHA inspection history. Wilful violations and repeat citations are major red flags that affect valuation and indemnification negotiations. #### Workers' Compensation Attorneys Quickly pull OSHA inspection records for an employer after a workplace injury. Complaint-initiated inspections and citations at the same facility are powerful supporting evidence. #### HR & Safety Recruiting Verify safety culture at prospective employers. A company with a pattern of Willful violations is a very different risk environment than one with occasional Programmed inspections. #### Investigative Journalism Surface the most dangerous workplaces in a state or industry. TRI, OSHA, and EPA data together form a complete picture of corporate environmental and safety records. #### Supply Chain Risk Screen logistics partners, warehousing vendors, and manufacturing contractors for OSHA history before signing contracts. --- ### MCP Tools #### `search_inspections` Search OSHA inspection records by company name, state, industry, and date range. **Arguments:** | Parameter | Type | Description | |-----------|------|-------------| | `establishment_name` | string | Company name (partial match). Example: `"Amazon"`, `"Tyson"` | | `state` | string | 2-letter state code. Example: `"WA"`, `"TX"` | | `naics_code` | string | NAICS industry code. Example: `"336111"` (auto mfg) | | `start_date` | string | Start of date range (YYYY-MM-DD) | | `end_date` | string | End of date range (YYYY-MM-DD) | | `inspection_type` | string | `Complaint`, `Programmed`, `Referral`, `Accident`, `Unprogrammed` | | `limit` | integer | Max results (default 25, max 100) | **Example query:** ```json { "name": "search_inspections", "arguments": { "establishment_name": "Amazon", "state": "WA", "start_date": "2022-01-01", "end_date": "2024-12-31", "limit": 10 } } ```` **Example response record:** ```json { "activity_nr": "1628394", "estab_name": "AMAZON FULFILLMENT CENTER", "site_address": "1901 E Sumner Ave", "site_city": "Sumner", "site_state": "WA", "site_zip": "98390", "naics_code": "493110", "open_date": "2023-03-15", "close_date": "2023-05-22", "insp_type": "Complaint", "total_violations": 4, "total_penalty": 156000.00, "source": "dol.gov/osha" } ``` **When the API is unavailable**, the actor returns a structured fallback instead of crashing: ```json { "_meta": { "error": "All OSHA API endpoints failed or returned non-JSON responses. The DOL Enforcement Data API may be temporarily unavailable. For manual queries visit: https://enforcedata.dol.gov", "fallback_tried": true } } ``` *** #### `search_violations` Search for OSHA violation citations by severity type, state, and date. **Arguments:** | Parameter | Type | Description | |-----------|------|-------------| | `violation_type` | string | `Willful`, `Serious`, `Other`, `Repeat` | | `state` | string | 2-letter state code | | `start_date` | string | Start date (YYYY-MM-DD) | | `limit` | integer | Max results (default 25, max 100) | **Violation types explained:** - **Willful** — Employer knowingly violated OSHA standards. Maximum penalty $156,259/violation. - **Serious** — Substantial probability of death or serious physical harm. Up to $15,625/violation. - **Repeat** — Same standard violated again within 5 years. Up to $156,259/violation. - **Other** — No direct or immediate relationship to job safety; generally lower risk. **Example query:** ```json { "name": "search_violations", "arguments": { "violation_type": "Willful", "state": "TX", "start_date": "2023-01-01", "limit": 20 } } ``` *** #### `get_inspection_stats` Aggregate OSHA inspection statistics for a state or NAICS industry sector. **Arguments:** | Parameter | Type | Description | |-----------|------|-------------| | `state` | string | 2-letter state code | | `naics_prefix` | string | First 2-4 digits of NAICS (e.g., `"31"` for all manufacturing) | | `year` | integer | Calendar year (2020–2024) | **Example response:** ```json { "state": "TX", "naics_prefix": "31", "period": "2023-01-01 to 2023-12-31", "total_inspections": 342, "total_violations": 891, "total_penalty_usd": 4820000.0, "avg_penalty_usd": 14094.15, "inspection_types": { "Complaint": 187, "Programmed": 112, "Referral": 31, "Accident": 12 }, "top_establishments": [ {"name": "TYSON FOODS", "inspections": 8}, {"name": "JBS USA", "inspections": 6} ], "source": "dol.gov/osha" } ``` *** ### Output Schema | Field | Type | Description | |-------|------|-------------| | `activity_nr` | string | Unique OSHA inspection activity number | | `estab_name` | string | Establishment (company) name | | `site_address` | string | Street address of inspected site | | `site_city` | string | City | | `site_state` | string | 2-letter state abbreviation | | `site_zip` | string | ZIP code | | `naics_code` | string | NAICS industry code | | `open_date` | string | Date inspection was opened (YYYY-MM-DD) | | `close_date` | string | Date inspection was closed | | `insp_type` | string | Inspection type (Complaint, Programmed, Referral, Accident) | | `total_violations` | integer | Total OSHA citations issued | | `total_penalty` | float | Total penalty amount in USD | | `source` | string | Always `"dol.gov/osha"` | *** ### Input Parameters | Parameter | Type | Default | Description | |-----------|------|---------|-------------| | `establishment_name` | string | `""` | Company/establishment name | | `state` | string | `""` | 2-letter state filter | | `naics_code` | string | `""` | NAICS code filter | | `start_date` | string | `""` | Start date (YYYY-MM-DD) | | `end_date` | string | `""` | End date (YYYY-MM-DD) | | `inspection_type` | string | `""` | Inspection type filter | | `limit` | integer | `25` | Max results (1–100) | | `serveMcp` | boolean | `false` | Enable MCP server mode | *** ### Modes of Operation #### Batch Mode (default) Run with input parameters. The actor fetches OSHA inspections, normalizes the results, and pushes them to the Apify dataset. Exits when complete. **Best for:** Scheduled monitoring, one-time company screening, pipeline automation. #### MCP Server Mode (`serveMcp: true`) Starts an HTTP server on port 4321 and runs indefinitely. **Best for:** Real-time AI assistant queries (Claude Desktop, Cursor, etc.). **Endpoints:** - `GET http://:4321/mcp/tools` — list tools - `POST http://:4321/mcp/call` — call a tool - `GET http://:4321/health` — health check *** ### Data Source **DOL Enforcement Data API** - URL: https://enforcedata.dol.gov - Auth required: None - Coverage: All OSHA federal enforcement inspections - Update frequency: Daily The primary endpoints used: - `enforcedata.dol.gov/api/osha_inspection` — inspection records - `enforcedata.dol.gov/api/osha_violation` — violation citations **Note on API Availability:** The DOL Enforcement Data API occasionally returns HTML error pages or 404s during maintenance windows. This actor handles those gracefully with structured fallback responses instead of crashing. If you receive a `_meta.error` response, the API may be temporarily down — retry in a few minutes. *** ### OSHA Inspection Types | Type | Description | Triggered By | |------|-------------|-------------| | Complaint | Formal worker or public complaint | Employee or anonymous tip | | Programmed | Planned based on targeting criteria | High-hazard industry lists | | Referral | Referred from another agency/source | Insurance carriers, other agencies | | Accident | Fatality or hospitalization of 3+ workers | Required reporting | | Unprogrammed | Unplanned inspection without complaint | Follow-up, monitoring | *** ### High-Risk NAICS Codes Industries most frequently inspected by OSHA: | NAICS | Industry | |-------|----------| | 236220 | Commercial/Industrial Building Construction | | 311615 | Poultry Processing | | 312120 | Breweries | | 336111 | Automobile Manufacturing | | 493110 | General Warehousing & Storage | | 562212 | Solid Waste Landfills | | 238910 | Site Preparation Contractors | | 321912 | Cut Stock, Resawing Lumber | | 311611 | Animal (except Poultry) Slaughtering | | 488119 | Other Airport Operations | *** ### OSHA Penalty Schedule (2024) | Violation Type | Maximum Penalty | |----------------|----------------| | Serious | $15,625 per violation | | Other-Than-Serious | $15,625 per violation | | Willful or Repeat | $156,259 per violation | | Failure to Abate | $15,625 per day | Penalties are adjusted annually for inflation. Multi-employer worksites can result in citations for both the controlling employer and the exposing employer. *** ### Example AI Prompts Once connected via MCP: - *"Search for OSHA inspections of Amazon warehouses in Washington state from 2022 to 2024"* - *"Show me all Willful violations in Texas manufacturing during 2023"* - *"Get OSHA inspection stats for the poultry processing industry (NAICS 311615) in 2023"* - *"Find Complaint-initiated inspections at construction companies in Florida"* - *"How many OSHA violations did Tyson Foods receive across all states last year?"* *** ### Error Handling Every error path returns a `_meta` record — the actor never throws an unhandled exception: ```json { "_meta": { "error": "human-readable description", "fallback_tried": true, "endpoints_tried": ["..."], "suggestion": "manual workaround if available" } } ``` This ensures downstream AI tools always receive valid JSON, even when the upstream OSHA API is unavailable. *** ### Technical Details - **Language:** Python 3.11 - **Runtime:** Apify Actor SDK v2 - **HTTP client:** httpx (async, 30s timeout per request) - **MCP server:** Pure asyncio TCP — no external web frameworks - **Port:** 4321 (MCP server mode) - **Endpoint fallback chain:** 3 endpoints tried in order before returning graceful error - **JSON vs HTML detection:** Content-Type header + body peek to guard against HTML error pages *** ### License Data sourced from DOL Enforcement Data, a US federal government public database in the public domain. Actor code is proprietary. # Actor input Schema ## `establishment_name` (type: `string`): Company or establishment name to search (partial match OK). Examples: 'Amazon', 'Tesla', 'Tyson Foods', 'Walmart Distribution'. Leave blank to search by state or NAICS only. ## `state` (type: `string`): 2-letter US state abbreviation to filter results. Examples: 'CA', 'TX', 'WA', 'OH', 'FL'. Leave blank to search all states. ## `naics_code` (type: `string`): 6-digit NAICS code to filter by industry. Examples: '336111' (Automobile Manufacturing), '311615' (Poultry Processing), '493110' (General Warehousing), '236220' (Commercial Construction). Partial codes (2-4 digits) also accepted. ## `start_date` (type: `string`): Filter inspections opened on or after this date (YYYY-MM-DD format). Example: '2023-01-01' ## `end_date` (type: `string`): Filter inspections opened on or before this date (YYYY-MM-DD format). Example: '2024-12-31' ## `inspection_type` (type: `string`): Filter by how the inspection was initiated. 'Complaint' = triggered by worker or public complaint. 'Programmed' = planned inspection based on targeting criteria. 'Referral' = referred by another agency. 'Accident' = fatality or catastrophe. Leave blank for all types. ## `limit` (type: `integer`): Maximum number of inspection records to return (max 100). 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 OSHA data. The actor will run continuously until stopped. Provides 3 MCP tools: search\_inspections, search\_violations, and get\_inspection\_stats. ## Actor input object example ```json { "establishment_name": "", "state": "", "naics_code": "", "start_date": "", "end_date": "", "inspection_type": "", "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/osha-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/osha-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/osha-intelligence-mcp --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=andrew_avina/osha-intelligence-mcp", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "OSHA Enforcement Intelligence MCP — 6M+ Inspection Records", "description": "Search millions of OSHA workplace safety inspections and violation records directly from your AI assistant. Query by company, state, industry code, date range, and inspection type — with full penalty history.", "version": "0.1", "x-build-id": "GzcGGqQEfKoqbQrLw" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/andrew_avina~osha-intelligence-mcp/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-andrew_avina-osha-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/andrew_avina~osha-intelligence-mcp/runs": { "post": { "operationId": "runs-sync-andrew_avina-osha-intelligence-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/andrew_avina~osha-intelligence-mcp/run-sync": { "post": { "operationId": "run-sync-andrew_avina-osha-intelligence-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "establishment_name": { "title": "Establishment Name", "type": "string", "description": "Company or establishment name to search (partial match OK). Examples: 'Amazon', 'Tesla', 'Tyson Foods', 'Walmart Distribution'. 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: 'CA', 'TX', 'WA', 'OH', 'FL'. Leave blank to search all states.", "default": "" }, "naics_code": { "title": "NAICS Code", "type": "string", "description": "6-digit NAICS code to filter by industry. Examples: '336111' (Automobile Manufacturing), '311615' (Poultry Processing), '493110' (General Warehousing), '236220' (Commercial Construction). Partial codes (2-4 digits) also accepted.", "default": "" }, "start_date": { "title": "Start Date", "type": "string", "description": "Filter inspections opened on or after this date (YYYY-MM-DD format). Example: '2023-01-01'", "default": "" }, "end_date": { "title": "End Date", "type": "string", "description": "Filter inspections opened on or before this date (YYYY-MM-DD format). Example: '2024-12-31'", "default": "" }, "inspection_type": { "title": "Inspection Type", "enum": [ "", "Complaint", "Programmed", "Referral", "Accident", "Unprogrammed" ], "type": "string", "description": "Filter by how the inspection was initiated. 'Complaint' = triggered by worker or public complaint. 'Programmed' = planned inspection based on targeting criteria. 'Referral' = referred by another agency. 'Accident' = fatality or catastrophe. Leave blank for all types.", "default": "" }, "limit": { "title": "Result Limit", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum number of inspection records to return (max 100). 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 OSHA data. The actor will run continuously until stopped. Provides 3 MCP tools: search_inspections, search_violations, and get_inspection_stats.", "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 } } } } } } } } } } ```