SolidWorks MCP
An MCP server that generates Python scripts for automating SolidWorks tasks by translating natural language requests into executable pywin32 code for creating parts and drawings.
README
SolidWorks MCP
This project implements an MCP server that provides a powerful tool for generating SolidWorks automation scripts using Python and the pywin32 library. It leverages a Large Language Model (LLM) to interpret user requests and produce runnable Python code for creating parts and drawings in SolidWorks.
Features
- SolidWorks Automation: Generate Python scripts to automate tasks within SolidWorks.
- LLM-Powered Code Generation: Utilizes an LLM to translate natural language requests into
pywin32code. - Easy Integration: Designed as a FastMCP server, allowing seamless integration with MCP-compatible clients and assistants.
- Timestamped Saving: Generated scripts include logic to save SolidWorks parts with unique, timestamped filenames.
How it Works
The solidgen tool exposed by this server takes a user request as input. It then constructs a detailed prompt for an LLM, instructing it to generate a Python script that uses pywin32 to perform the requested SolidWorks operation. The generated script includes boilerplate for initializing SolidWorks and saving the created part.
Getting Started
Prerequisites
- Python 3.x
fastmcppywin32- Access to an LLM
- SolidWorks
Installation
- Clone this repository:
git clone https://github.com/arhamgarg/solidworks-mcp.git cd solidworks-mcp - Install dependencies using
uv:uv sync
Running the Server
To run the FastMCP server:
python server.py
Once running, the server will expose the solidgen tool, which can be called by an MCP client.
Usage (via an MCP Client)
An MCP client can call the solidgen tool with a user_request string.
Example of how an MCP client might call the tool:
{
"mcpServers": {
"solidworks-mcp": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/PARENT/FOLDER/solidworks-mcp",
"run",
"server.py"
]
}
}
}
The tool will return a Markdown-formatted Python code block containing the generated SolidWorks automation script.
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。