fusion-mcp
Open-source MCP server for controlling Autodesk Fusion 360 from any AI agent, enabling 3D modeling operations via natural language.
README
fusion-mcp
Open-source MCP server for controlling Autodesk Fusion 360 from any AI agent. just Python.
MCP Client ──stdio──▶ MCP Server (Python) ──TCP──▶ Fusion 360 Add-in ──▶ Fusion API
Setup
1. Clone and install
With uv (recommended):
git clone https://github.com/prim-design/fusion-mcp.git
cd fusion-mcp
uv pip install -e .
With pip (macOS/Linux):
git clone https://github.com/prim-design/fusion-mcp.git
cd fusion-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -e .
With pip (Windows):
git clone https://github.com/prim-design/fusion-mcp.git
cd fusion-mcp
python -m venv .venv
.venv\Scripts\activate
pip install -e .
Requires Python 3.10+.
2. Install the Fusion 360 add-in
Copy the addin/ folder to Fusion's add-ins directory:
macOS:
cp -r addin/ "$HOME/Library/Application Support/Autodesk/Autodesk Fusion 360/API/AddIns/FusionMCP"
Windows:
xcopy /E addin "%APPDATA%\Autodesk\Autodesk Fusion 360\API\AddIns\FusionMCP\"
Then in Fusion 360: Shift+S → Add-Ins → select FusionMCP → Run (optionally check "Run on Startup").
3. Connect your MCP client
Claude Code:
claude mcp add fusion-mcp -- /path/to/fusion-mcp/.venv/bin/fusion-mcp
Claude Desktop — add to claude_desktop_config.json:
{
"mcpServers": {
"fusion-mcp": {
"command": "/path/to/fusion-mcp/.venv/bin/fusion-mcp"
}
}
}
Works with any MCP client — run .venv/bin/fusion-mcp as a stdio server.
Tools (51)
| Category | Tools |
|---|---|
| Sketch | create_sketch finish_sketch draw_line draw_rectangle draw_circle draw_arc draw_polygon draw_spline draw_slot |
| 3D Features | extrude revolve sweep loft |
| Modifications | fillet chamfer shell draft |
| Patterns | pattern_rectangular pattern_circular mirror |
| Booleans | combine split_body |
| Components | create_component list_components delete_component move_component rotate_component rename |
| Joints | create_joint (all 7 types) set_joint_limits drive_joint list_joints |
| Rigid Groups | create_rigid_group list_rigid_groups delete_rigid_group |
| Inspection | get_design_info get_body_info measure check_interference fit_view screenshot |
| Export/Import | export_stl export_step export_3mf import_mesh |
| Utility | undo delete_body delete_sketch batch |
| Escape Hatch | execute_python — run arbitrary Python inside Fusion with full API access |
Joint types
create_joint supports all 7 Fusion joint types: rigid, revolute, slider, cylindrical, pin_slot, planar, ball. Uses as-built joints by default (components stay in place).
Screenshot
screenshot captures the viewport as a PNG image returned directly to the AI. Supports preset views (front, back, top, bottom, left, right, iso) and custom camera positions via eye_x/y/z + target_x/y/z.
Important notes
- Units: All lengths in cm, all angles in degrees
- Z-negation gotcha: On XZ plane, sketch +Y = world -Z. On YZ plane, sketch +X = world -Z.
- Thread safety: The add-in dispatches all API calls to Fusion's main thread via CustomEvent
- Escape hatch:
execute_pythonruns arbitrary Python inside Fusion for anything not covered by curated tools
How it works
The MCP server (server/) runs as a stdio process your AI agent connects to. It forwards commands over a TCP socket to the Fusion 360 add-in (addin/), which runs inside Fusion and executes API calls on the main thread using Fusion's CustomEvent system for thread safety.
License
MIT
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。