jgs-magic-sysmlv1-mcp
MCP bridge to live SysML v1 models in CATIA Magic / Cameo Systems Modeler (No Magic MSoSA). Lets Claude Code or any MCP agent query, audit, and edit MBSE models — blocks, requirements, diagrams, parametrics, traceability — over a local, air-gapped connection.
README
<!-- Copyright (c) 2026 JG Systems Consulting Ltd. All Rights Reserved. -->
JGS SysML v1 MCP Bridge
AI-to-CATIA Magic bridge for SysML v1 models. Exposes your SysML v1 project to AI agents via the Model Context Protocol (MCP).
Install with your AI agent
Copy everything in the block below and paste it into your coding agent (Claude Code, Cursor, etc.). It will do the parts it safely can and hand back the few desktop steps it cannot do for you.
You are installing jgs-magic-sysmlv1-mcp, a proprietary MCP bridge (JG Systems Consulting
Ltd.) that lets MCP clients work with live SysML v1 models in CATIA Magic Systems of
Systems Architect (MSOSA 2026x). Repository: https://github.com/jgsystemsconsulting/jgs-magic-sysmlv1-mcp (version 0.1.1).
Do this in order:
1. Read README.md, docs/install.md, docs/configuration.md, and docs/licensing.md in
this repository so you understand the full install and prerequisites (CATIA Magic
2026x, Python >= 3.11, an MCP client such as Claude Code).
2. Do the scriptable steps: install the Python server with `pip install ./server`
(see docs/install.md for the exact command), create my MCP client config from
`examples/.mcp.json.example` (fill in placeholders; never invent secrets/tokens),
and place my licence file as described in docs/licensing.md.
3. STOP: these two steps run on my desktop app and you cannot do them for me:
a. Copy the contents of `plugin/` into my CATIA Magic user plugins directory
(the exact path is in docs/install.md).
b. Restart CATIA Magic.
Tell me the target path and wait for me to confirm I have done both.
4. After I confirm, verify the bridge by calling the `ping` MCP tool and report the
result. If it fails, walk me through docs/configuration.md.
5. This is licensed software: point me at LICENSE and docs/licensing.md and note the
FREE / PRO / ENTERPRISE tiers. Never invent, commit, or share licence keys.
Install from the Claude Code marketplace
This repo ships a Claude Code plugin manifest, so you can add it as a marketplace and install from inside Claude Code:
/plugin marketplace add jgsystemsconsulting/jgs-magic-sysmlv1-mcp
/plugin install jgs-magic-sysmlv1-mcp
The marketplace install registers the bridge; the desktop steps (CATIA Magic plugin JAR
- restart) still run on your machine. See docs/install.md.
What's Included
plugin/: CATIA Magic plugin JAR (copy to your plugins directory)server/: Python MCP server (install withpip install ./server)docs/: Installation guide and configuration referencetools/: Licence verification utilityexamples/: Sample.mcp.jsonconfiguration
Quick Start
See docs/install.md for full installation instructions.
Requirements
- CATIA Magic Systems of Systems Architect 2026x
- Python 3.11 or later
Support & Security
- Support / licensing: JG Systems Consulting Ltd.
- Report a security issue: open a private security advisory on this repository. Please do not open public issues for vulnerabilities, and do not email keys or licence material.
Found a bug? (agents and humans) If a tool returns malformed or incorrect output, open
an issue with the Bug Report form at ../../issues/new/choose. Include the server version,
the tool name, and the exact tool call and its output. This is a release repo - the fix is
applied upstream by the maintainer, so please file an issue rather than a pull request.
Licence
Proprietary: see LICENSE and docs/licensing.md.
Copyright (c) 2026 JG Systems Consulting Ltd. All Rights Reserved.
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。