inventor-mcp
MCP server for parametric 3D modeling in Autodesk Inventor, enabling natural language control of sketching, extrusion, hole features, and sheet metal operations.
README
inventor-mcp
MCP server for parametric 3D modeling in Autodesk Inventor — drive Inventor with Claude (or any MCP client) in natural language.
Build real parametric parts — flanges, shafts, nuts, brackets, sheet-metal enclosures — by talking to an AI assistant. The server wraps Inventor's COM API with high-level, millimeter-based tools and ships with battle-tested knowledge of Inventor 2026 API quirks that aren't documented anywhere else.
You: "Build a DIN 934 M16 hex nut with proper conical chamfers"
Claude: creates sketch → hexagon → extrude → tapped M16×2 hole →
revolve-cut chamfers → done. Fully parametric, dimensioned sketches.
Features
- 34 MCP tools: sketching, extrude/revolve, native hole features (drilled / tapped / counterbore), fillets, chamfers, circular patterns, sheet metal (Face / Flange / Cut with Flat Pattern support), parameters
execute_pythonpower tool — run arbitrary Python against the live COM connection with a persistent namespace (escape hatch for anything not covered by dedicated tools)- Auto-reporting — every feature operation returns a volume/topology delta (
Hole1 | V 23497 (-503 mm³) | F7 E14), so the AI can self-verify each step - Transactions — wrap multi-step builds, roll back everything with one call
- Hot reload — edit the API wrapper and reload without restarting the MCP client
- Topology helpers — find edges/faces by coordinates instead of guessing indices
- Parametric discipline — projected origin points, symmetry constraints, dimensioned sketches that survive parameter changes
Requirements
- Windows with Autodesk Inventor (developed and tested on Inventor 2026; older versions may need enum adjustments — see docs/inventor-api-notes.md)
- Python 3.12+
pip install "mcp[cli]" pywin32
Installation
-
Clone this repository:
git clone https://github.com/NeonGlay/inventor-mcp.git -
Install dependencies:
pip install "mcp[cli]" pywin32 -
Register the server with your MCP client. For Claude Code, add to
.mcp.jsonin your project root (see.mcp.json.example):{ "mcpServers": { "inventor": { "command": "python", "args": ["-m", "src.server"], "cwd": "C:/path/to/inventor-mcp" } } } -
Start Inventor, then ask your AI assistant to build something.
Do NOT use
win32com.client.gencache.EnsureDispatchin your own scripts against the same Python install — the generatedgen_pycache breaksGetActiveObject. If it happens: delete%LOCALAPPDATA%\Temp\gen_py. See the API notes for the full story.
Skills (optional, recommended)
The skills/ directory contains two Agent Skills that teach Claude the workflow and the Inventor 2026 API quirks:
- inventor-modeling — core patterns: units, sketch discipline, hole placement, sheet metal, diagnostic verification, common failure modes
- inventor-din-parts — parametric recipes for DIN/ISO standard parts (hex nuts DIN 934, bolts DIN 933, washers DIN 125, flanges DIN 2573) with dimension tables
Install by copying into your skills directory:
cp -r skills/inventor-modeling ~/.claude/skills/
cp -r skills/inventor-din-parts ~/.claude/skills/
Why this exists
Inventor's COM API documentation is wrong or silent about many things in recent versions. This project encodes empirically verified knowledge:
- Correct Inventor 2026 enum values (
kPartDocumentObject = 12290, dimension orientation19201/19202/19203, …) ChamferFeatures.AddUsingDistance(EdgeCollection, d)— the 2026 replacement for the removedCreateChamferDefinition- Sheet-metal
FlangeDefinition: the Distance argument is silently ignored; the real height is set viafeature.Definition.HeightExtent.Distance.Expression(and the angle is in radians — pass90and you get 5156°) CreateLinearPlacementDefinitionrequires aBiasPointargument that dynamic dispatch won't tell you about- Edge indices renumber after every feature; fillets shift adjacent edges
- …and more in docs/inventor-api-notes.md
Architecture
src/server.py FastMCP server — tool definitions (stdio transport)
src/inventor_api.py InventorConnection — COM wrapper, all geometry logic (mm units)
skills/ Agent Skills for Claude
docs/ Hard-won API knowledge
Contributing
Contributions welcome! Especially valuable:
- Testing on Inventor 2024/2025 (enum values may differ — please report)
- Assembly (IAM) and drawing (IDW) support
- More DIN/ISO part recipes
- Bug reports with the exact COM error and Inventor version
License
MIT — see LICENSE.
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。