APS MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@APS MCP ServerShow me my available hubs"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
APS MCP Server
A minimal MCP server integrating Autodesk ACC APIs via APS toolkit.
Video Overview
Setup
Option 1: Using uv (recommended)
Install uv if you don't have it:
curl -LsSf https://astral.sh/uv/install.sh | shCopy
.env.sampleto.envand fill in your credentials:cp .env.sample .envCreate and activate a virtual environment:
uv venv # On Windows: .venv\Scripts\activate # On Unix or MacOS: source .venv/bin/activateInstall dependencies:
uv pip install -r requirements.txtRun the MCP server:
python aps_dm_server.py
Option 2: Using pip
Copy
.env.sampleto.envand fill in your credentials:cp .env.sample .envCreate and activate a virtual environment:
python -m venv .venv # On Windows: .venv\Scripts\activate # On Unix or MacOS: source .venv/bin/activateInstall dependencies:
pip install -r requirements.txtRun the MCP server:
python aps_dm_server.py
Integration with Claude Desktop
To use this MCP server with Claude Desktop:
Make sure you have Claude Desktop installed (download from Claude.ai)
Open your Claude Desktop configuration file:
code ~/Library/Application\ Support/Claude/claude_desktop_config.jsonCreate it if it doesn't exist.
Add the appropriate configuration:
Option A: Direct Python from virtual environment (most reliable)
{ "mcpServers": { "acc": { "command": "/ABSOLUTE/PATH/TO/YOUR/.venv/bin/python", "args": [ "/ABSOLUTE/PATH/TO/YOUR/aps_dm_server.py" ], "env": { "PYTHONPATH": "/ABSOLUTE/PATH/TO/YOUR/PROJECT/FOLDER" } } } }Replace paths with absolute paths to your environment and project.
Option B: Using uv
{ "mcpServers": { "acc": { "command": "/ABSOLUTE/PATH/TO/uv", "args": [ "--directory", "/ABSOLUTE/PATH/TO/YOUR/PROJECT/FOLDER", "run", "aps_dm_server.py" ] } } }Find the absolute path to
uvby runningwhich uvin your terminal.Save the file and restart Claude Desktop completely
Look for the hammer icon in Claude Desktop to access the ACC tools
macOS Specific Setup
macOS users may encounter permission issues when integrating with Claude Desktop:
Permission Issues: If you see errors like
Operation not permittedin logs:Open System Preferences → Privacy & Security → Full Disk Access
Add Terminal and Claude applications by clicking the "+" button
Working Directory Issues: If you see errors about current directory not existing:
Always use absolute paths in your configuration
Consider storing projects in locations with fewer permissions restrictions (e.g., Documents folder)
Finding the correct Python path: To get the exact path to your virtual environment's Python:
source .venv/bin/activate # Activate your environment first which python # Get the full pathChecking logs for troubleshooting:
tail -n 50 -f ~/Library/Logs/Claude/mcp*.log
Requirements
Python 3.11 or higher
Dependencies listed in requirements.txt
System Architecture
This MCP server acts as a bridge between Claude AI and the Autodesk APS platform. The diagram below illustrates how data flows through the system:

Your query to Claude triggers tool selection
Claude sends MCP requests to your local server
The MCP server connects to APS/ACC using your credentials
Data flows back to Claude which processes and formats results
Available Tools
The MCP server exposes the following tools:
get_hubs: Get all available hubsget_projects: Get all projects within a hubget_project_files: Get files in a specific folder of a projectget_versions: Get version information for a specific item
Troubleshooting
If you encounter issues with Claude Desktop integration:
Server not showing up:
Check configuration file syntax (valid JSON)
Use absolute paths everywhere
Restart Claude Desktop completely
Permission errors:
Grant Full Disk Access to Terminal and Claude
Try using Python directly rather than through uv
Try moving the project to a location with fewer restrictions
Environment errors:
Ensure all dependencies are installed
Try using the direct path to Python in your virtual environment
Check your
.envfile has correct Autodesk credentials
Logs check:
tail -n 50 -f ~/Library/Logs/Claude/mcp*.logManual testing: Test your server works by running it directly:
cd /path/to/your/project source .venv/bin/activate python aps_dm_server.py
Using with OpenAI Agents SDK
This project includes integration with the OpenAI Agents SDK, allowing you to use the MCP server with an OpenAI agent.
Make sure your
.envfile includes your OpenAI API key:OPENAI_API_KEY=your_openai_api_keyInstall the additional dependencies:
uv pip install openai>=1.31.0Run the agent:
python main_agent.py
This will start an interactive session where you can ask the agent questions about your Autodesk projects.
Dependencies and Licensing
This project uses the following open source components:
aps-toolkit - A library for Autodesk Platform Services (GPL-3.0)
mcp - Multimodal Capability Protocol implementation
python-dotenv - Environment variable management
openai and openai-agents - OpenAI integration
This project is licensed under the GNU General Public License v3.0 as required by the aps-toolkit dependency.
Disclaimer
This software is provided "as is", without warranty of any kind, express or implied. This is a prototype for demonstration purposes only. The author takes no responsibility for any damages or issues that may arise from using this software. Use at your own risk.
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/kpphillips/aps-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server