Zerubroberts Safetyculture MCP Server

🚀 SafetyCulture MCP Server

This is a Model Context Protocol (MCP) server built for the SafetyCulture API. This project allows users to query their SafetyCulture data using natural language after providing an API key.

✨ Features

• Query SafetyCulture data using natural language.
• Analyze inspection data and trends.
• Compare safety metrics across different periods and categories.
• Visualize trends of inspections over time.

📦 Installation

1. Clone this repository.
2. Install dependencies: pip install -r requirements.txt
3. Copy example.env to .env and configure your SafetyCulture API key.
4. Run the server using one of the following methods:
   • run_server.bat - Run the server with the configuration in the .env file.
   • run_with_key.bat YOUR_API_KEY - Run the server with the provided API key.

💻 Usage Examples

Test API

To test if your SafetyCulture API key is working:

test_api.bat YOUR_API_KEY

Other test options:

• test_api.bat - Run the test interactively (prompts for an API key).
• test_api.bat feed YOUR_API_KEY - Test only the Feed API.
• test_api.bat url - Check which API URLs are accessible without authentication.

Use with Claude for Desktop

1. Install Claude for Desktop.
2. Configure Claude for Desktop to use this MCP server by editing the configuration file ~/Library/Application Support/Claude/claude_desktop_config.json (Mac) or %APPDATA%\Claude\claude_desktop_config.json (Windows).
3. Add the following configuration:

{
    "mcpServers": {
        "safetyculture": {
            "command": "python",
            "args": [
                "/path/to/your/project/src/main.py"
            ]
        }
    }
}

4. Restart Claude for Desktop.
5. Use the MCP tool to query your SafetyCulture data with the following questions:
   • "How many inspections were completed at this site in the past three months?"
   • "Compare any trends in reported injuries in this category."

Available Tools

Authentication

• authenticate: Authenticate with the SafetyCulture API using an API key.

Inspection Data (Using Feed API)

• get_inspections: Get SafetyCulture inspections for a specific time period.
• get_inspection_trends: Analyze trends of SafetyCulture inspections over time.
• compare_injury_reports: Compare injury reports for two time periods.

Action Data (Using Feed API)

• get_actions: Get SafetyCulture actions for a specific time period.
  • Filter by status (e.g., "in progress", "completed", "overdue").
  • Filter by priority (e.g., "low", "medium", "high").
  • View detailed information for each action.
• get_action_details: Get detailed information for a specific action by ID.

📚 Documentation

About the Feed API

This MCP server uses the SafetyCulture Feed API, which provides a simple way to access collections of resources:

• /feed/inspections: For listing inspections with various filtering parameters.
• /feed/actions: For listing actions with various filtering parameters. The Feed API is recommended over individual resource endpoints when multiple items need to be listed.

Development

Project Structure

.
├── README.md
├── requirements.txt
├── example.env
└── src/
    ├── main.py                      # Main entry point
    ├── safetyculture_api/           # SafetyCulture API client
    │   ├── __init__.py
    │   └── client.py                # API client implementation
    ├── tools/                       # MCP tools
    │   ├── __init__.py
    │   └── inspection_tools.py      # Inspection and action tools
    └── utils/                       # Utility modules
        ├── __init__.py
        ├── analysis.py              # Data analysis utilities
        ├── config.py                # Configuration management
        └── date_utils.py            # Date parsing utilities

Development Log

Initial Setup

• Create the project structure.
• Set up the Git repository.
• Add README and requirements.
• Implement the SafetyCulture API client.
• Add MCP tools to query inspection data.
• Add utility modules for date parsing and data analysis.
• Add configuration management.