effectustasi/autodesk-inventor-mcp
FreeNot checkedConnect AI assistants to a live Autodesk Inventor session over COM: inspect bodies and features, find sliver faces in imported models, dry-run Unwrap, and scrip
About
Connect AI assistants to a live Autodesk Inventor session over COM: inspect bodies and features, find sliver faces in imported models, dry-run Unwrap, and script the Inventor API.
README
effectustasi/autodesk-inventor-mcp MCP server
An MCP server that gives AI agents (Claude Code, Claude Desktop, Cursor, Codex…) a live connection to Autodesk Inventor.
Ask your agent things like "which faces in this imported STEP are tiny slivers?" or "will Unwrap work on these 12 faces?" and it reads the answer straight from the open model.
- Zero dependencies: one Python file, standard library only.
- Live: talks to the running Inventor session over COM (via Windows PowerShell). No export, no file round-trips.
- Units you think in: lengths in mm, areas in mm² (Inventor's internal unit is cm; the server converts).
- Safe by default:
unwrap_trycreates the feature, measures the result and deletes it again unless you passkeep: true.
Requirements
- Windows with Autodesk Inventor installed and running (developed against Inventor 2027)
- Python 3.9+
Install
Clone or download server.py, then register it with your agent.
Claude Code
claude mcp add inventor -- python C:\path\to\inventor-mcp\server.py
Claude Desktop / Cursor / any MCP client (mcpServers config):
{
"mcpServers": {
"inventor": {
"command": "python",
"args": ["C:\\path\\to\\inventor-mcp\\server.py"]
}
}
}
Tools
| Tool | What it does |
|---|---|
status |
Inventor version and open documents |
model_info |
Bodies (face/edge/vertex counts, bounding box in mm) and the feature tree of a part |
smallest_faces |
The N smallest faces with area and center. Finds import defects fast |
face_neighbors |
Faces that share an edge with a given face |
unwrap_try |
Tries an Unwrap on a face set and reports success, timing, result area and bounding box, the details the GUI doesn't show. Rolls back by default |
script |
Runs arbitrary PowerShell against Inventor's COM API, with $inv and helpers predefined |
Face indices are 1-based and stable for a given body as long as the model doesn't change.
⚠️ About the script tool
script executes any PowerShell your agent writes, with your user's permissions. That's what makes it powerful (anything in the Inventor API is reachable), and it's also why you should keep your agent's tool-approval prompts on for it. If you don't want it, delete its entry from TOOLS in server.py.
All other tools pass arguments as data, never as code.
Example (illustrative)
You: The STEP I imported won't unwrap. What's wrong with it?
Agent: (calls
smallest_faces) Body 1 has 412 faces; the 6 smallest are under 0.01 mm², clustered around (12.4, -3.1, 40.0). (callsface_neighborson face 287) They sit between two large B-spline faces, which is the classic sliver from a bad tessellation export. (callsunwrap_trywithout them) Unwrap succeeds in 1.8 s when those 6 faces are excluded.
Contributing
Issues and PRs are welcome, especially new read-only tools (assemblies, sketches, iProperties, sheet metal), Inventor-version compatibility reports, and non-English Windows fixes. See the issues labeled good first issue.
License
MIT. Not affiliated with or endorsed by Autodesk. Autodesk and Inventor are trademarks of Autodesk, Inc.
More tools by effectustasi
- agent-receipts: Skills that make AI coding agents prove "done" with real test output
- blender-dlss5-neural-rendering: Blender viewport and renders through DLSS 5 neural rendering
- metahuman-face-capture: MetaHuman face capture from a webcam in Blender
- unreal-groom-alembic-exporter: Export UE Groom assets (MetaHuman hair) to Alembic
Installing effectustasi/autodesk-inventor-mcp
This server has no published package — it is built from source. Open the repository and follow its README.
▸ github.com/effectustasi/autodesk-inventor-mcpFAQ
Is effectustasi/autodesk-inventor-mcp MCP free?
Yes, effectustasi/autodesk-inventor-mcp MCP is free — one-click install via Unyly at no cost.
Does effectustasi/autodesk-inventor-mcp need an API key?
No, effectustasi/autodesk-inventor-mcp runs without API keys or environment variables.
Is effectustasi/autodesk-inventor-mcp hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install effectustasi/autodesk-inventor-mcp in Claude Desktop, Claude Code or Cursor?
Open effectustasi/autodesk-inventor-mcp on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Opencode Omniroute Plugin
OpenCode plugin for the OmniRoute AI Gateway. Drives dynamic model discovery, /connect auth flow, and multi-instance OmniRoute providers via the official @openc
by GitHub ActionsRoblox Studio
Enables AI coding tools to control Roblox Studio for workspace exploration, instance manipulation, and script management. It provides tools for playtesting, sce
by paralovAntigravity Drawio
MCP server that enables AI assistants to create, parse, render, and validate Draw.io diagrams programmatically.
by S-SUJAN-SFetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
by xuzexin-hzMCP-Agent
A simple, composable framework to build agents using Model Context Protocol by [LastMile AI](https://www.lastmileai.dev)
by lastmile-aiSpring AI MCP Client
Provides auto-configuration for MCP client functionality in Spring Boot applications.
mcp.natoma.ai
A Hosted MCP Platform to discover, install, manage and deploy MCP servers by [Natoma Labs](https://www.natoma.ai)
Compare effectustasi/autodesk-inventor-mcp with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs
