Fusion 360 MCP Server

@Joelalbon

Basic information

About Fusion 360 MCP Server

Remote control solution for Fusion 360 using client-server architecture. Features JSON socket communication, modular design with Python server and client library, plus Fusion 360 add-in. Enables command monitoring, remote execution, and model data retrieval for automation workflo

Fusion 360 MCP Server config

No standard config provided

This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.

Repository

Fusion 360 MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Fusion 360 MCP Server?

A Master Control Program (MCP) server for Autodesk Fusion 360 that enables remote control and automation of Fusion 360 operations. It acts as a bridge between external applications and the Fusion 360 API, allowing remote execution of commands and retrieval of model information.

How to use Fusion 360 MCP Server?

Install Python 3.6+ and copy the files. Run python server.py to start the server (default listens on 127.0.0.1:8080). Install the Fusion 360 add-in by copying the folder to the AddIns directory and loading it from the "Scripts and Add-ins" dialog. Use the provided MCPClient class to connect, send commands, and retrieve data.

Key features of Fusion 360 MCP Server

Three components: server, client library, and Fusion 360 add-in.
JSON-based TCP protocol for client-server communication.
Remote execution of Fusion 360 commands and retrieval of model info.
Optional LLM integration via OpenAI API key.
Supports fusion_command, get_model_info, llm_request, and other message types.

Use cases of Fusion 360 MCP Server

Automate repetitive Fusion 360 tasks from external scripts.
Remotely control Fusion 360 without direct interaction.
Retrieve model information for analysis or reporting.
Integrate with LLMs to generate or modify designs based on text requests.

Frequently asked questions

What are the system requirements?

Python 3.6 or higher is required. No additional Python packages are needed for basic functionality; the `openai` package is optional for LLM features. Fusion 360 must be installed and the add-in must be loaded.

How does communication work between client and server?

The server and clients communicate using a simple JSON-based protocol over TCP sockets. Each message is a JSON object with a `type` field indicating the message type (e.g., `fusion_command`, `get_model_info`, `command_result`).

How can I extend the server to support new commands?

Add new message types to the protocol, implement handlers in the server, add corresponding methods to the client, and implement the actual functionality in the Fusion 360 add-in.

Where should the Fusion 360 add-in be installed?

Copy the entire folder containing `fusion360_mcp_addin.py`, `client.py`, and the `resources` directory to Fusion 360's **AddIns** directory. Then load it from the "Scripts and Add-ins" dialog.

I see an install error about more than one file. How do I fix this?

Create a new add-in (Python) in Fusion 360, edit it, copy the `fusion360_mcp_addin.py` source to the new file, save, open the new file location, and copy `client.py` and the resource folder to that location. Then restart Fusion 360.

Comments

More Developer Tools MCP servers

ArtiBot Cloud MCP - Zhijiangyun 智匠云

bofob

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

Official Porkbun MCP Server

Porkbun LLC

Official Porkbun MCP server, maintained by Porkbun. Check domain availability and pricing, register, renew and transfer domains, and manage DNS records, nameservers, URL forwarding, glue records, DNSSEC and domain contac

Mcp-Warden

ermoluk

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott