PTC-MCP Integration Server
Integrates PTC Windchill and Creo Parametric with LLM-based clients via the Model Context Protocol, enabling natural language interaction with PLM and CAD systems for tasks like part search, BOM retrieval, model operations, and exports.
README
PTC-MCP Integration Server
Model Context Protocol (MCP) server for integrating PTC Windchill and Creo Parametric with LLM-based clients.
Overview
The PTC-MCP Integration Server provides a standardized gateway between MCP clients (ChatGPT Desktop, Claude Desktop, Agents SDK) and PTC's enterprise PLM and CAD systems. It enables natural language interaction with Windchill and Creo through structured, auditable workflows.
Features
- MCP Protocol Support: Full implementation of Model Context Protocol
- Windchill Integration: Read operations for parts, BOMs, and documents
- Creo Automation: Model operations, exports, and parameter extraction
- Security: Enterprise-grade authentication, authorization, and audit logging
- Configuration: Centralized configuration management
Requirements
- Node.js >= 18.0.0
- TypeScript >= 5.3.0
- Access to PTC Windchill (REST/OData API)
- Creo Parametric with J-Link/OTK (for Creo automation)
Installation
# Install dependencies
npm install
# Build the project
npm run build
# Run in development mode
npm run dev
# Run production build
npm start
Configuration
Copy .env.example to .env and configure:
# Windchill Configuration
WINDCHILL_BASE_URL=https://your-windchill-server.com
WINDCHILL_USERNAME=service-account
WINDCHILL_PASSWORD=password
# Creo Configuration
CREO_JLINK_PATH=C:/Program Files/PTC/Creo X.X/Common Files/x86e_win64/obj/jlink
CREO_EXPORT_PATH=./exports
# MCP Server Configuration
MCP_SERVER_NAME=ptc-mcp-server
MCP_SERVER_VERSION=1.0.0
LOG_LEVEL=info
Usage
As MCP Server (stdio)
The server runs as an MCP server accessible via stdio:
node dist/index.js
MCP Client Configuration
Configure in your MCP client (e.g., Claude Desktop):
{
"mcpServers": {
"ptc-mcp": {
"command": "node",
"args": ["/path/to/ptc-mcp-integration-server/dist/index.js"]
}
}
}
Available Tools
Windchill Tools
windchill_search_part- Search for partswindchill_get_part- Get part detailswindchill_get_bom- Get bill of materialswindchill_get_docs- Get associated documents
Creo Tools
creo_open_model- Open Creo modelcreo_export_step- Export as STEPcreo_export_pdf- Export drawing as PDFcreo_get_parameters- Extract parameters
Development
# Type checking
npm run type-check
# Linting
npm run lint
# Testing
npm test
# Watch mode
npm run dev
Project Structure
ptc-mcp-server/
├── src/
│ ├── mcp/ # MCP protocol implementation
│ ├── windchill/ # Windchill connector
│ ├── creo/ # Creo automation service
│ ├── security/ # Security layer
│ └── config/ # Configuration management
├── tests/ # Test files
├── config/ # Configuration files
└── docs/ # Documentation
Documentation
License
MIT
Support
For issues and questions, please refer to the project documentation or create an issue.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。