Fusion 360 MCP Server
A model context protocol (MCP) server for Autodesk Fusion that provides resources and tools from ADSK to an AI client such as Claude or Cursor.
Joe-Spencer
README
Fusion 360 MCP Server
This repository contains a Model Context Protocol (MCP) server for Autodesk Fusion 360. It enables AI assistants like Claude to interact directly with Fusion 360 using the MCP protocol.
Overview
The server is implemented as a Fusion 360 add-in that exposes Fusion 360's functionality through MCP. This allows AI agents to:
- Access information about the current design
- Create and modify design elements
- Receive context-specific prompts for CAD tasks
The repository includes:
MCPserve/
- The Fusion 360 add-in that implements the MCP serverclient.py
- A testing utility to verify server functionalityinstall_mcp_for_fusion.py
- A helper script to install the MCP package for Fusion 360's Python environment
How It Works
The MCP server runs within Fusion 360 and exposes a communication channel that AI agents can use to:
- Access resources - Get information about the current design, components, parameters, etc.
- Use tools - Perform actions like creating sketches, adding parameters, or displaying messages
- Get prompts - Receive specialized prompt templates for CAD-related tasks
Requirements
- Autodesk Fusion 360
- Python 3.7+ (for installation and testing)
- MCP Python SDK:
pip install "mcp[cli]"
(must be installed in Fusion 360's Python environment)
Installation
1. Install MCP in Fusion 360's Python Environment
Fusion 360 uses its own Python environment, separate from your system's Python. The MCP package must be installed there.
Using the Installer Script (Recommended):
python install_mcp_for_fusion.py
This script will:
- Find all Fusion 360 Python installations on your system
- Install the MCP package with CLI extras for each installation
- Verify the installation was successful
Manual Installation:
If the installer script doesn't work, you can manually install the package:
- Find Fusion 360's Python executable (usually in
Autodesk\webdeploy\production\[version]\Python
) - Install the package:
"[Fusion Python Path]\python.exe" -m pip install "mcp[cli]"
2. Install the Fusion 360 Add-in
- In Fusion 360, click on "Tools" tab → "Add-Ins" → "Scripts and Add-Ins"
- Click the green "+" button in the "My Add-Ins" tab
- Browse to and select the
MCPserve
folder from this repository - Click "Open" to add it to your add-ins
- Select it and click "Run" to start it
Using the MCP Server with AI Assistants
The server enables AI assistants like Claude to interact with Fusion 360 in several ways:
Resources
AI assistants can access these resources:
fusion://active-document-info
- Basic information about the active documentfusion://design-structure
- Detailed structure of the current designfusion://parameters
- User parameters defined in the document
Tools
AI assistants can use these tools:
message_box
- Display a message box in Fusion 360create_new_sketch
- Create a new sketch on a specified planecreate_parameter
- Create a new parameter with specified values
Prompts
AI assistants can use specialized prompts:
create_sketch_prompt
- Expert guidance for creating sketchesparameter_setup_prompt
- Expert guidance for setting up parameters
Testing the Server
Use the included client script to test if the server is functioning correctly:
python client.py --test-connection
To test specific functionality:
# Test displaying a message box
python client.py --test-message-box
# Test listing available resources
python client.py --list-resources
# Test listing available tools
python client.py --list-tools
# Test listing available prompts
python client.py --list-prompts
Communication Methods
The MCP server supports two methods of communication:
- MCP Protocol over HTTP SSE - The standard MCP protocol implementation, accessible at
http://127.0.0.1:3000/sse
- File-based Communication - A backup method using files in the
mcp_comm
directory for environments that can't directly connect to the HTTP endpoint
Technical Details
The server implementation:
- Runs as a background thread in Fusion 360 to maintain responsiveness
- Automatically creates ready files to signal when it's available
- Registers resources, tools, and prompts with the MCP protocol
- Monitors for file-based commands when HTTP communication isn't possible
Contributing
Contributions are welcome! Feel free to submit issues or pull requests.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Model Context Protocol (MCP) for the Python SDK
- Autodesk Fusion 360 for the powerful CAD/CAM platform
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.
MCP Package Docs Server
Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
@kazuph/mcp-taskmanager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Linear MCP Server
Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.
mermaid-mcp-server
A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.
Jira-Context-MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor

Linear MCP Server
A Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.