manufacturing-mcp
Manufacturing MCP
制造设备数据探索与故障风险分析的 MCP(Model Context Protocol)基于 AI Agent 项目。
数据集
本项目使用 AI4I 2020 Predictive Maintenance Dataset。这是模拟真实工业现场预测性维护数据而生成的合成数据集,由 10,000 条设备运行观测值和 14 列组成。没有缺失值。
每条观测值中包含 产品等级、空气温度和工艺温度、转速、扭矩、刀具磨损时间等,同时记录了 设备是否故障 及 故障类型。因此可用于以下预测性维护场景:
设备状态监控(Monitoring)
故障风险分类(Classification)
异常条件检测(Anomaly Detection)
主要列
各列的含义和单位请参见 数据集列文档。
数据样本
以下是原始 CSV 的前 3 条观测值。
UDI | Product ID | Type | Air temperature [K] | Process temperature [K] | Rotational speed [rpm] | Torque [Nm] | Tool wear [min] | Machine failure | TWF | HDF | PWF | OSF | RNF |
1 | M14860 | M | 298.1 | 308.6 | 1551 | 42.8 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
2 | L47181 | L | 298.2 | 308.7 | 1408 | 46.3 | 3 | 0 | 0 | 0 | 0 | 0 | 0 |
3 | L47182 | L | 298.1 | 308.5 | 1498 | 49.4 | 5 | 0 | 0 | 0 | 0 | 0 | 0 |
Related MCP server: Sparkplug MCP Server
开发环境配置
本项目使用 Python 3.12 或更高版本。在 WSL Ubuntu 24.04 的项目根目录下激活虚拟环境并安装开发依赖。
source mcp/bin/activate
python -m pip install --upgrade pip
python -m pip install -e ".[dev]"参考 .env.example 编写本地 .env 文件。包含实际 API Key 的 .env 不会纳入 Git。
cp -n .env.example .env
chmod 600 .env代码变更后运行测试、lint 和格式检查。
pytest
ruff check .
ruff format --check .当前 Python 包位于 src/manufacturing_mcp,测试位于 tests。应用程序配置通过 src/manufacturing_mcp/config.py 从环境变量和 .env 文件中加载。
运行 PostgreSQL
使用 Docker Compose 在后台运行 PostgreSQL 容器。
docker compose up -d postgres
docker compose ps如果 postgres 服务的状态为 healthy,则代表正常。若需直接访问 PostgreSQL,请使用以下命令。
docker compose exec postgres sh -c 'psql -U "$POSTGRES_USER" -d "$POSTGRES_DB"'连接结束后请输入 \q 退出。停止容器时,请使用以下命令。
docker compose downPostgreSQL 数据保存在 postgres_data Docker 卷中,因此即使停止或重新创建容器,数据也会被保留。
来源与版权
项目代码:Copyright © 2026 Johyeongseob。基于 MIT License 发布。
数据集:AI4I 2023200 Predictive Maintenance Dataset(2020),UCI Machine Learning Repostory,https://doi.org/10.24432/C5HS5C
相关论文:Stephan Matzka, “TUMMka,” *always, Explainable Artificial Intelligence for Maintenance Applications,” 2020 Third International Conference on Artificial Intelligence for Industries (AI4I), pp. 69–74, https://doi.org/10.1109/AI4I49448.2020.00023
数据集许可证:Creative Commons Attribution 4.0 International (CC BY 4.0). 允许对数据集进行分享和修改,但使用时须注明原作者与来源。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityAmaintenanceEnables AI assistants to analyze vibration data, detect machinery faults, and generate professional diagnostic reports through natural conversation.3474MIT
- FlicenseAqualityDmaintenanceEnables natural language interaction with industrial IoT devices using Sparkplug B, allowing users to query real-time data, analyze historical metrics, and monitor device status.49
- FlicenseNot gradedqualityBmaintenanceAn AI agent system that monitors manufacturing equipment health using the Model Context Protocol (MCP). Enables answering natural language questions about equipment status, maintenance, and anomalies through MCP tools.
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to analyze plant-floor data using OEE, Pareto, SPC, and yield-loss calculations, providing continuous-improvement insights from manufacturing data.1
Related MCP Connectors
Cross-OEM industrial machine intelligence: identity, normalization, automation, attestation.
The grounded data layer for any LLM: governed SQL, metrics, lineage and catalog over your data.
Find relevant security data from Sentinel data lake for building effective agents. More:aka.ms/s/de
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/johyeongseob/manufacturing-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server