Predictive MaintenanceBLOCK
MCP server for predictive maintenance and machinery fault diagnosis. Gives AI assistants evidence-based vibration analysis - FFT, envelope, bearing fault detection, ISO 20816-3 severity - with a measured, blind CWRU benchmark. Local-first: raw signals never leave your machine. Includes a Claude Code
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.python.org/downloads/) [](https://doi.org/10.5281/zenodo.17611542) [](https://github.com/LGDiMaggio/predictive-maintenance-mcp/actions/workflows/tests.yml) [](https://codecov.io/gh/LGDiMaggio/predictive-maintenance-mcp) [](https://opensource.org/licenses/MIT) [](https://glama.ai/mcp/servers/LGDiMaggio/predictive-maintenance-mcp)
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
929a06315119OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add predictive-maintenance-mcp -- None predictive-maintenance-mcp==0.13.0
Trust audit
BLOCKgrade D · trust 60/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (3 observation(s))
- Network
- declared (1 observation(s))
- Shell
- declared (6 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (25)
model = pickle.load(f)
scaler = pickle.load(f)
pca = pickle.load(f)
model = pickle.load(f)
scaler = pickle.load(f)
__import__(module)
.zenodo.json
module = importlib.import_module(t.fn.__module__)
module = importlib.import_module(fn.__module__)
module = __import__(name)
advisory["signal_id"] = "../../../etc/passwd"
advisory["provenance"]["signal_id"] = "../../../etc/passwd"
signal_file="../../etc/passwd.csv",
hostile = ["../secret.txt", "../../etc/passwd", str(secret)]
"../../evil",
curl http://127.0.0.1:8000/sse
proxy_pass http://127.0.0.1:8000;
<action type="Rewrite" url="http://127.0.0.1:8000/{R:1}" />proxy_pass http://127.0.0.1:8000;
--upstream=http://127.0.0.1:8000 \
<img src="https://raw.githubusercontent.com/LGDiMaggio/predictive-maintenance-mcp/main/assets/claude_gif.gif" alt="Animated demo: a full diagnostic conversation in Claude Desktop, from loading a vibra
assets/claude_gif.gif
assets/envelope_signals.png
assets/plugin.gif
Gates applied: no_behavioural_pass.
929a06315119full audit observations/trust-audit/mcp-server/lgdimaggio__predictive-maintenance.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 929a06315119 | BLOCK | D | 60 | first audit |
Questions
What is the Predictive Maintenance MCP server?
MCP server for predictive maintenance and machinery fault diagnosis. Gives AI assistants evidence-based vibration analysis - FFT, envelope, bearing fault detection, ISO 20816-3 severity - with a measured, blind CWRU benchmark. Local-first: raw signals never leave your machine. Includes a Claude Code
Is Predictive Maintenance safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (60/100) and found 5 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Predictive Maintenance need?
No credential environment variables were found in its source, so it appears to need none.
How does Predictive Maintenance run?
It speaks sse, stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as predictive-maintenance-mcp.
How current is this page?
The grade is for one exact copy of the source (929a06315119), read on 2026-10-07. The repository is watched and re-audited when it changes.