Predictive Maintenance MCP Server

Give your AI assistant evidence-based vibration diagnostics — machinery fault detection, ISO-cited severity, and diagnostic reports built to support and accelerate expert decision-making.

An open-source MCP server that turns LLMs into condition monitoring assistants for reliability engineers. Its core design rule: the server refuses to guess. No diagnosis is ever inferred from filenames or statistical parameters alone — a fault indication requires matching spectral evidence. Every severity claim cites ISO 20816-3, and the evaluative wording in reports is authored by the server, not improvised by the model. The AI orchestrates the analysis and presents the evidence — detected fault frequencies, matched fault patterns, severity zones — while the final judgment stays with the engineer. Also available as a Claude Code plugin with 8 diagnostic skills.

See It in Action

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

Choose Your Path

Quick Start

Get running in ~3 minutes. On Windows, one script wires everything into Claude Desktop — it installs the venv, pre-compiles dependencies, and writes claude_desktop_config.json for you (OneDrive / cloud-sync paths included):

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

Restart Claude Desktop, then try:

"Load real_train/OuterRaceFault_1.csv and check if the bearing is healthy."

pip install predictive-maintenance-mcp

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

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

Benchmark

A blind, reproducible diagnostic-accuracy benchmark on the public CWRU Bearing Data Center dataset (12 kHz drive-end subset: 60 fault records + 4 normal baselines). Fault labels never reach the system under test — signals enter under opaque ids, a separate scorer is the only label reader, and blindness, checksum integrity, and determinism are enforced by CI-run guard tests, not prose. Results are stratified by the per-record diagnosability grades of the Smith & Randall (2015) reference study, so records that study found undiagnosable by any classical method are reported separately instead of inflating or deflating the headline.

On records the reference study grades clearly diagnosable (Y1+Y2, 44 records): characteristic fault frequency detected on 44/44, correct fault ranked first on 34/44 (77.3%), and 9/9 on the textbook-signature (Y1) stratum. On the 4 healthy baselines, 2 records raised a false indication under the same criterion.

The numbers above are read from the committed, re-runnable artifact (results.json) and drift-guarded by CI: every value is bound to its key in the artifact, and a mismatch fails the build. Methodology, blind protocol, and honest-benchmarking notes: docs/benchmark-methodology.md. Reproduce with:

python -m benchmarks.cwru all

What Can It Do?

Point the AI at a vibration signal → get the evidence behind the fault — detected frequencies, matched fault patterns, ISO-cited severity — to support your call.

The AI doesn't guess: it calls 41 specialized MCP endpoints (38 tools + 3 prompts) running locally on your machine. Every signal is referenced by a single signal_id handle from load to report. Your data never leaves your infrastructure.

Full endpoint reference, grouped by category: Tool Catalog.

Claude Code Plugin

The project includes a plugin for Claude Code with domain-specific skills that activate automatically during conversation.

/plugin marketplace add LGDiMaggio/predictive-maintenance-mcp
/plugin install predictive-maintenance@predictive-maintenance-marketplace

The plugin adds 8 skills that activate automatically based on context (bearing-diagnosis, gear-diagnosis, quick-screening, report-generation, anomaly-detection, signal-management, documentation-search, prognostics), 2 agents that run multi-step diagnostic workflows end-to-end and hand you the evidence (diagnostic-pipeline, signal-explorer), and 3 commands for quick entry points (/pm-diagnose, /pm-screen, /pm-report).

Full skill, agent, and command reference: Plugin README.

Reports

All analysis tools generate interactive HTML reports you can open in any browser — pan, zoom, hover for details. Also supports structured Word (.docx) exports.

Sample Data Included

The project ships with 20 real bearing vibration signals from production machinery tests — ready to use out of the box: a training set (2 healthy baselines + 12 fault signals, inner and outer race) and a test set (1 healthy baseline + 5 fault signals).