Osha Compliance Assistant

Created By
contextkits4 months ago
Check workplace safety compliance against OSHA General Industry standards (29 CFR 1910) with cited regulation sections and corrective actions.
Overview

OSHA Compliance Assistant (MCP Server)

MIT License Python 3.10+ MCP Compatible

Give Claude instant access to OSHA General Industry compliance knowledge (29 CFR 1910). Ask workplace safety questions and get cited verdicts with regulation sections and corrective actions.


Get Your API Key

Free tier available — no credit card required.

TierDaily CallsPrice
Sandbox10/dayFree
Developer500/day$79/mo
Team2,000/day$199/mo
Enterprise10,000/day$499/mo

Installation

pip install mcp httpx

Claude Desktop Setup

Add to claude_desktop_config.json:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "osha-compliance": {
      "command": "python",
      "args": ["/path/to/osha-compliance-assistant/server.py"],
      "env": {
        "OSHA_API_KEY": "your_api_key_here"
      }
    }
  }
}

Available Tool

compliance_check

Check whether a workplace scenario complies with OSHA General Industry standards.

Input:

{
  "scenario": "Describe the workplace situation or safety question"
}

Output: Cited compliance verdict with relevant regulation section and recommended actions.


Coverage

OSHA 29 CFR 1910 General Industry standards including fall protection, machine guarding, electrical safety, lockout/tagout, PPE, fire safety, hazard communication, forklifts, and more.


Disclaimer

AI-generated guidance only. Not a substitute for official OSHA publications or certified safety inspections. Always verify with a qualified safety professional.


License

MIT — see LICENSE

An MCP server that gives Claude instant access to OSHA General Industry compliance knowledge (29 CFR 1910). Ask any workplace safety question and get a cited YES/NO verdict with the relevant regulation section and corrective actions.


What It Does

Claude can answer questions like:

  • "Do I need guardrails on a 4-foot platform?"✅ YES - Section 1910.23(c)(1)
  • "Can I store propane cylinders near an exit door?"❌ NO - Section 1910.253(b)
  • "Is automatic restart after a power outage allowed on saws?"❌ NO - Section 1910.213(a)(9)

Covers 30+ high-priority OSHA 1910 topics including fall protection, lockout/tagout, electrical safety, machine guarding, fire extinguishers, forklifts, PPE, hazard communication, and more.


Get Your API Key

Free tier available. Get your API key instantly via Telegram:

📧 Email gcsmst at gmail.com with subject "MCP API Key" to get your free Sandbox key

TierDaily CallsPrice
Sandbox10/dayFree
Developer500/day$79/mo
Team2,000/day$199/mo
Enterprise10,000/day$499/mo

Installation

pip install mcp httpx

Claude Desktop Configuration

Add to your claude_desktop_config.json:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "osha-compliance": {
      "command": "python",
      "args": ["/path/to/osha-compliance-assistant/server.py"],
      "env": {
        "OSHA_API_KEY": "your_api_key_here"
      }
    }
  }
}

Replace /path/to/osha-compliance-assistant/server.py with the actual path where you cloned this repo.


Available Tool

compliance_check

Check whether a workplace scenario complies with OSHA General Industry standards.

Input:

{
  "scenario": "string — describe the workplace situation or safety question"
}

Output:

Plain text response with:

  • ✅ YES or ❌ NO verdict
  • Cited OSHA section (e.g. Section 1910.23(c)(1))
  • 3 bullet points with specific requirements
  • Corrective actions where applicable

Example:

User: Do workers need hard hats when doing electrical panel work?

Claude (via OSHA MCP):
❌ NO - Section 1910.135
- Hard hats (ANSI Z89.1) required when overhead electrical hazard exists
- Electrical panel work requires Class E rated hard hat for arc flash protection
- Employer must conduct hazard assessment before work begins (1910.132(d))

⚠️ AI analysis only — verify with official OSHA standards or a safety professional.

Topics Covered

SectionTopic
1910.23Guardrails & Fall Protection
1910.25Portable Ladders
1910.36-37Exit Routes & Doors
1910.95Noise & Hearing Conservation
1910.133Eye & Face Protection
1910.135Head Protection
1910.147Lockout/Tagout (LOTO)
1910.157Fire Extinguishers
1910.178Forklifts
1910.212Machine Guarding
1910.215Grinders
1910.242Compressed Air
1910.253Oxygen & Fuel Cylinders
1910.303Electrical Safety
1910.1200Hazard Communication (SDS)
5(a)(1)General Duty Clause

Disclaimer

This tool provides AI-generated compliance guidance based on OSHA 1910 General Industry standards. It is not a substitute for professional safety consultation, official OSHA publications, or certified safety inspections. Always verify with official OSHA standards or a qualified safety professional before making compliance decisions.


License

MIT License — see LICENSE

Server Config

{
  "mcpServers": {
    "osha-compliance": {
      "command": "python",
      "args": [
        "server.py"
      ],
      "env": {
        "OSHA_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}
Project Info
Created At
4 months ago
Updated At
3 months ago
Author Name
contextkits
Star
-
Language
-
License
-
Category

Recommend Servers

View All
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

8 hours ago