Skip to main content
Glama
LGDiMaggio

Predictive Maintenance MCP Server

by LGDiMaggio
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Related Servers

Alternatives to Predictive Maintenance MCP Server

No user-submitted related servers found.

    Related Servers

    • LineSight

      marcoaguzman
      F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to analyze plant-floor data using OEE, Pareto, SPC, and yield-loss calculations, providing continuous-improvement insights from manufacturing data.
      1
      -

    • mcp-server-mcsa

      LGDiMaggio
      A
      license
      A
      quality
      C
      maintenance
      Enables predictive maintenance for electric motors by analyzing stator current signals to detect faults like broken rotor bars, bearing defects, and eccentricity, using spectral and envelope analysis techniques.
      21
      50 PyPI
      9
      MIT

    • Auto-Manager MCP

      Maxpeng59
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables natural language analysis of mechanical test data files (CSV, TDMS, MDF) by providing tools for channel statistics, spectrum analysis, rainflow fatigue counting, thermal state detection, and report generation.
      MIT

    • FactoryMind AI

      Puru20Srini
      F
      license
      Not graded
      quality
      D
      maintenance
      Enables engineers and plant managers to interact with manufacturing systems using natural language, providing machine health analysis, KPI dashboards, predictive maintenance, and automated workflow execution via MCP.
      -
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.1/5.0

    Scored across 34 tools

    Disambiguation3/5

    Many tools are clearly separated by resource or analysis type, and the descriptions are detailed. However, several boundaries are fuzzy—diagnose_vibration and generate_diagnostic_report expose nearly the same integrated pipeline, and the frequency/report cluster (analyze_fft, compute_psd, compute_spectrogram_stft, generate_fft_report) requires careful reading to choose correctly.

    Naming Consistency4/5

    Names consistently follow lower_snake_case verb_noun and are broadly predictable: list_*, load_*, generate_*_report, analyze_*. Minor deviations—plot_signal versus the generate_*_report family, compute_* versus analyze_* for related analyses, and list_html_reports actually listing all report types—keep it from being perfectly uniform.

    Tool Count2/5

    34 tools is well above the 25+ threshold for a coherent set and will burden an agent with selection overhead. Many report generators could be consolidated, and the frequency-analysis/report cluster overlaps enough that the same underlying capability is exposed through several different tools.

    Completeness4/5

    The server covers the full predictive-maintenance workflow: signal generation/loading/inspection, time- and frequency-domain analysis, bearing checks, ISO severity, anomaly detection, integrated diagnostic reports, and RUL estimation. Gaps are minor—no model listing/deletion, no report deletion, no raw signal export—but the main load→analyze→diagnose→report flow has no dead ends.

    Maintenance

    ActivityActive
    ResponsivenessSlow

    Resources