AssetOpsBench

What it does

AssetOpsBench is a comprehensive framework designed for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance. It enables AI to interact with industrial sensor data, failure mode records, and work order systems to automate reliability engineering and predictive maintenance.

Tools

• IoT Tools: get_sites, get_history, get_assets, get_sensors for infrastructure discovery and telemetry.
• FMSR Tools: get_sensors, get_failure_modes, get_failure_sensor_mapping for fault diagnosis.
• TSFM Tools: forecasting and timeseries_anomaly_detection for predictive health monitoring.
• Work Order Tools: get_work_order_distribution and predict_next_work_order for maintenance planning.
• Vibration Tools: compute_fft_spectrum and compute_envelope_spectrum for signal analysis.

Installation

To use AssetOpsBench as an MCP server, clone the repository and install the package:

git clone https://github.com/IBM/AssetOpsBench.git
cd AssetOpsBench
pip install -e .

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "assetopsbench": {
      "command": "python3",
      "args": ["-m", "assetopsbench.mcp_server"]
    }
  }
}

Supported hosts

• claude