Predictive Maintenance MCP Server

Give any AI assistant the ability to analyze vibration data, detect machinery faults, and generate professional diagnostic reports — through natural conversation.

An open-source MCP server and predictive maintenance AI agent that turns LLMs into condition monitoring assistants. Engineers describe what they need in plain language; the AI calls the right analysis tools and delivers results — bearing fault detection, risk assessment, anomaly detection, and remaining useful life estimation. Also available as a Claude Code plugin with 7 diagnostic skills. It's designed to support and accelerate expert decision-making.

Quick Start

pip install predictive-maintenance-mcp

Windows — automatic setup (recommended):

Clone the repo and run the setup script — it installs the venv, pre-compiles dependencies, and writes claude_desktop_config.json automatically (handles OneDrive/cloud-sync paths too):

git clone https://github.com/LGDiMaggio/predictive-maintenance-mcp.git
cd predictive-maintenance-mcp
.\setup_claude.ps1

Manual config (Windows / macOS / Linux):

Find the full path to uvx on your system (where uvx on Windows, which uvx on macOS/Linux), then add to %APPDATA%\Claude\claude_desktop_config.json (Windows) or ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):

{
  "mcpServers": {
    "predictive-maintenance": {
      "command": "/full/path/to/uvx",
      "args": ["predictive-maintenance-mcp"],
      "env": { "UV_LINK_MODE": "copy" }
    }
  }
}

Why the full path? Claude Desktop launches servers with a minimal PATH that often omits user-local tool directories (e.g. ~/.local/bin). Using the full path to uvx avoids a silent "command not found" failure. On Windows the typical path is C:\Users\<you>\.local\bin\uvx.exe.

Restart Claude Desktop. You're ready — try: "Load real_train/OuterRaceFault_1.csv and check if the bearing is healthy."

More options: install from source · VS Code setup · Docker / HTTPS deployment · use with local LLMs (Ollama)

See It in Action

Full diagnostic workflow: load signal → spectral analysis → fault detection → severity assessment → report generation

What Can It Do?

Upload a vibration signal → get a professional diagnosis through conversation.

... View full README on GitHub