FreeCAD MCP Next
MCP server that connects FreeCAD to AI assistants via a local workbench and XML-RPC bridge, enabling natural language control of FreeCAD.
README
FreeCAD MCP Next
Русский
FreeCAD MCP Next связывает FreeCAD с MCP-клиентами: Codex, GitHub Copilot Chat в Visual Studio Code и другими совместимыми ассистентами.
Проект состоит из двух локальных процессов:
- Workbench внутри FreeCAD открывает XML-RPC на
127.0.0.1:9875. - Команда
freecad-mcpработает как stdio MCP-сервер для AI-клиента.
Быстрый старт из исходников
Требования: FreeCAD 1.0 или новее, Python 3.12+, Git и
uv.
git clone https://github.com/Lumitorus/freecad-mcp-next.git
cd freecad-mcp-next
uv sync
uv run python scripts/install_addon.py
Перезапустите FreeCAD, выберите рабочее окружение MCP Addon и нажмите Start RPC Server. Затем подключите MCP-клиент:
codex mcp add freecad -- uv --directory "C:\path\to\freecad-mcp-next" run freecad-mcp
Для Copilot скопируйте .vscode/mcp.example.json в
.vscode/mcp.json, замените путь и выполните в VS Code команду MCP: List Servers.
Полная инструкция: docs/installation.ru.md.
Отдельная благодарность
neka-nat/freecad-mcp за основу проекта.
English
FreeCAD MCP Next connects FreeCAD to MCP clients such as Codex, GitHub Copilot Chat in Visual Studio Code, and other compatible assistants.
The project uses two local processes:
- A FreeCAD workbench exposes XML-RPC on
127.0.0.1:9875. - The
freecad-mcpcommand provides an stdio MCP server to the AI client.
Quick start from source
Requirements: FreeCAD 1.0 or newer, Python 3.12+, Git, and
uv.
git clone https://github.com/Lumitorus/freecad-mcp-next.git
cd freecad-mcp-next
uv sync
uv run python scripts/install_addon.py
Restart FreeCAD, select the MCP Addon workbench, and click Start RPC Server. Then connect your MCP client:
codex mcp add freecad -- uv --directory "C:\path\to\freecad-mcp-next" run freecad-mcp
For Copilot, copy .vscode/mcp.example.json to
.vscode/mcp.json, replace the path, and run MCP: List Servers in VS Code.
Full guide: docs/installation.en.md.
Special thanks to
neka-nat/freecad-mcp for providing
the foundation of this project.
Development and releases
Pull requests run linting, unit tests, package builds, and addon validation on Windows, macOS, and Linux. Release Please maintains a version/changelog PR from Conventional Commits. Merging that PR creates a draft release, verifies it on all three operating systems, attaches the artifacts, and publishes it:
- a Python wheel and source distribution;
FreeCADMCP-<version>.zipfor manual FreeCAD installation;- SHA-256 checksum files;
- a GitHub Release containing all artifacts.
See CONTRIBUTING.md and docs/releasing.md.
Continue, Ollama, and terminal clients
Ollama provides the local language model; Continue acts as the MCP client and connects that model to FreeCAD tools. A ready-to-copy configuration is available at examples/config/continue-ollama.yaml.
Detailed Russian and English instructions:
License and acknowledgements
Maintained by Lumitorus and distributed under the MIT License.
Special thanks to
neka-nat/freecad-mcp for the
foundation of this project. See NOTICE.md.
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。