Motor Current Signature Analysis MCP Server

A Model Context Protocol (MCP) server for Motor Current Signature Analysis (MCSA) - non-invasive spectral analysis and fault detection in electric motors using stator-current signals. Its 21 documented tools cover compute, signal, detect, file. It runs locally over stdio via the published package.

People who work with compute, signal and detect and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-05-29 · ★ 9 · #86 OF 120 MAINTAINED DEVOPS & MONITORING · VERIFIED 2026-09-18

MIT · Python servers · how we verify → /methodology

01 · Install Motor Current Signature Analysis

Claude Code

claude mcp add lgdimaggio-mcp-motor-current-signature-a -- uvx mcp-server-mcsa

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "lgdimaggio-mcp-motor-current-signature-a": {
      "command": "uvx",
      "args": [
        "mcp-server-mcsa"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package mcp-server-mcsa - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.LGDiMaggio is GitHub-verified and matches the repo owner

03 · What Motor Current Signature Analysis can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can inspect a signal file format and metadata without loading, load a current signal from CSV / WAV / NPY file → returns signal_id, calculate expected fault frequencies for all common fault types, and detect and characterise peaks in a spectrum.

Capability map

Tools grouped from the project's README - what Motor Current Signature Analysis lets an agent do.

Compute

7 tools - e.g. Calculate expected fault frequencies for all common fault types; Calculate BPFO, BPFI, BSF, FTF from bearing geometry; Single-sided FFT amplitude spectrum → returns spectrum_id

compute_fault_frequencies · compute_bearing_frequencies · compute_spectrum · compute_power_spectral_density · compute_envelope_spectrum · compute_band_energy…

Detect

4 tools - e.g. BRB fault index with severity classification; Air-gap eccentricity detection via sidebands; Stator inter-turn short circuit detection

detect_broken_rotor_bars · detect_eccentricity · detect_stator_faults · detect_bearing_faults

read & search

2 tools - e.g. Detect and characterise peaks in a spectrum; List all signals and spectra persisted on disk

find_spectrum_peaks · list_stored_data

Inspect

1 tool - e.g. Inspect a signal file format and metadata without loading

inspect_signal_file

Load

1 tool - e.g. Load a current signal from CSV / WAV / NPY file → returns signal_id

load_signal_from_file

Calculate

1 tool - e.g. Compute slip, sync speed, rotor frequency from motor data

calculate_motor_params

Preprocess

1 tool - e.g. DC removal, filtering, normalisation, windowing pipeline → returns new signal_id

preprocess_signal

Generate

1 tool - e.g. Synthetic motor current with optional faults → returns signal_id

generate_test_current_signal

Latest releases

v0.2.2 · 2026-02-16

What's new · CITATION.cff - GitHub now shows the "Cite this repository" button with full author metadata · .zenodo.json - Zenodo automatically picks up title, author, ORCID, and keywords on each release · ORCID…

v0.2.1 · 2026-02-09

Abstract · mcp-server-mcsa is an open-source server implementing the Model Context Protocol (MCP) for Motor Current Signature Analysis (MCSA) - a non-invasive condition-monitoring technique that detects mechanical and…

v0.2.0 · 2026-02-07

What's New · Persistent Data Store (~/.mcsa_data/) · Signals and spectra are now saved to disk as compressed .npz files and referenced by short IDs (sig_xxxx, spec_xxxx). Large arrays never enter the chat context.…

04 · Who maintains Motor Current Signature Analysis

Motor Current Signature Analysis is maintained by lgdimaggio. It's the only MCP server we track from this author; the repo dates to Feb 2026.

05 · Facts

category
DevOps & monitoring - ranked #86 of 120 actively-maintained DevOps & monitoring servers as of 2026-09-18.
registry
io.github.LGDiMaggio/mcp-server-mcsa (active, first published 2026-02-06 · 3 versions)
packages
pypi:mcp-server-mcsa

06 · Motor Current Signature Analysis FAQ

Is Motor Current Signature Analysis still maintained?

Yes - as of 2026-09-18, its last commit was 2026-05-29. We re-verify nightly.

What can Motor Current Signature Analysis do?

With this server connected, an agent can inspect a signal file format and metadata without loading, load a current signal from CSV / WAV / NPY file → returns signal_id, calculate expected fault frequencies for all common fault types, and detect and characterise peaks in a spectrum.

How do I install Motor Current Signature Analysis?

Run `uvx mcp-server-mcsa`. You can also paste the ready-made client config above.

Does Motor Current Signature Analysis run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Motor Current Signature Analysis