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:

{
  "name": "search_inspections",
  "arguments": {
    "establishment_name": "Amazon",
    "state": "WA",
    "start_date": "2022-01-01",
    "end_date": "2024-12-31",
    "limit": 10
  }
}

Example response record:

{
  "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:

{
  "_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:

{
  "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:

{
  "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://<run-url>:4321/mcp/tools — list tools
• POST http://<run-url>:4321/mcp/call — call a tool
• GET http://<run-url>: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:

{
  "_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.