Predictive Maintenance
AI-Powered Predictive Maintenance & Fault Diagnosis through Model Context Protocol. An open-source framework for integrating Large Language Models with predictive maintenance and fault diagnosis workflows.
What is Predictive Maintenance?
Predictive Maintenance is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ai-powered predictive maintenance & fault diagnosis through model context protocol. an open-source framework for integrating large language models with predictive maintenance and fault diagnosis workf...
AI-Powered Predictive Maintenance & Fault Diagnosis through Model Context Protocol. An open-source framework for integrating Large Language Models with predictive maintenance and fault diagnosis workflows.
This server falls under the Data Science & ML and Monitoring & Observability categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- AI-Powered Predictive Maintenance & Fault Diagnosis through
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx predictive-maintenanceConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Predictive Maintenance
The Predictive Maintenance MCP Server is an open-source framework that integrates Large Language Models with industrial condition monitoring and fault diagnosis workflows. It exposes 52 MCP endpoints covering vibration signal acquisition, FFT/envelope spectral analysis, bearing fault classification (inner race, outer race, ball, cage faults), ISO 20816-3 severity assessment, and Remaining Useful Life (RUL) estimation. Engineers and data scientists use it to ask natural-language questions about machinery health, automatically triggering multi-step signal analysis and generating HTML or Word diagnostic reports without writing a single line of analysis code.
Prerequisites
- Python 3.11 or later installed
- uv package manager installed (https://github.com/astral-sh/uv)
- Claude Desktop or another MCP-compatible client
- Vibration data files in CSV, WAV, MAT, NPY, or Parquet format
- Windows, macOS, or Linux operating system
Install via pip or uvx
Install the package using pip. The server is also available through uvx, which is the recommended runtime because it isolates dependencies automatically.
pip install predictive-maintenance-mcpLocate the full path to uvx
Claude Desktop requires the absolute path to uvx to avoid a silent 'command not found' failure. Run the following command to find it and copy the output.
which uvxAdd the server to Claude Desktop configuration
Open claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json, Windows: %APPDATA%\Claude\claude_desktop_config.json) and add the server block. Replace /full/path/to/uvx with the path from the previous step.
{
"mcpServers": {
"predictive-maintenance": {
"command": "/full/path/to/uvx",
"args": ["predictive-maintenance-mcp"],
"env": { "UV_LINK_MODE": "copy" }
}
}
}Restart Claude Desktop
Fully quit and reopen Claude Desktop so it picks up the new MCP server configuration. You should see the predictive-maintenance server listed in the connected tools panel.
Load a vibration signal and run a health check
Point the AI at one of your vibration files and ask it to assess bearing health. The server will automatically load the file, compute FFT and envelope spectra, classify any fault patterns, and return a severity rating.
Generate a diagnostic report
Ask for a structured HTML or Word report after analysis. The server embeds charts, fault markers, and ISO 20816-3 severity zone classifications directly into the output document.
Predictive Maintenance Examples
Client configuration
Add this block to claude_desktop_config.json to connect Claude Desktop to the predictive maintenance server.
{
"mcpServers": {
"predictive-maintenance": {
"command": "/usr/local/bin/uvx",
"args": ["predictive-maintenance-mcp"],
"env": { "UV_LINK_MODE": "copy" }
}
}
}Prompts to try
These prompts exercise the server's core fault detection and prognostics capabilities.
- "Load OuterRaceFault_1.csv and check if the bearing is healthy."
- "Run envelope analysis on vibration.csv and identify any characteristic fault frequencies."
- "Estimate the remaining useful life of the bearing in sensor_data.npy using Weibull regression."
- "Generate an HTML diagnostic report for all signals in the /data/motors folder."
- "Classify the severity of the vibration in pump_reading.wav according to ISO 20816-3."Troubleshooting Predictive Maintenance
Claude Desktop shows the server as disconnected or never discovers tools
Ensure you used the absolute path to uvx (not just 'uvx') in the command field of claude_desktop_config.json. Run 'which uvx' and paste the full path.
File loading fails for MAT or NPY formats
These formats require scipy and numpy to be available. Install them in the same environment: pip install scipy numpy. If using uvx, add them to the project dependencies or use pip install predictive-maintenance-mcp[all].
UV_LINK_MODE copy error on some Linux systems
If the server fails to start with a link mode error, try removing the UV_LINK_MODE env key entirely, or set it to 'symlink' instead of 'copy'.
Frequently Asked Questions about Predictive Maintenance
What is Predictive Maintenance?
Predictive Maintenance is a Model Context Protocol (MCP) server that ai-powered predictive maintenance & fault diagnosis through model context protocol. an open-source framework for integrating large language models with predictive maintenance and fault diagnosis workflows. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Predictive Maintenance?
Follow the installation instructions on the Predictive Maintenance GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Predictive Maintenance?
Predictive Maintenance works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Predictive Maintenance free to use?
Yes, Predictive Maintenance is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Predictive Maintenance Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Predictive Maintenance? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Predictive Maintenance in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Predictive Maintenance?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.