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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.