aps

Simple prototype MCP server integrating Autodesk APIs

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

Command

claude mcp add --transport stdio kpphillips-aps-mcp-server python aps_dm_server.py \
  --env APS_TENANT="your_aps_tenant_id_or_domain" \
  --env APS_API_KEY="your_aps_api_key (if applicable)" \
  --env APS_CLIENT_ID="your_aps_client_id" \
  --env OPENAI_API_KEY="your_openai_api_key" \
  --env APS_CLIENT_SECRET="your_aps_client_secret"

How to use

This MCP server provides a lightweight bridge between Claude Desktop (and OpenAI agents) and Autodesk APS through the aps_dm_server.py implementation. The server exposes a small set of tools that let you inspect and navigate Autodesk ACC data via the APS toolkit. Available tools include get_hubs (list all hubs), get_projects (list projects within a hub), get_project_files (retrieve files in a project folder), and get_versions (fetch version information for an item). You can run the server directly with Python, or via a Python environment manager as recommended in the setup instructions. Once the server is running, configure Claude Desktop (or your OpenAI agent workflow) to point at the APS MCP server, using absolute paths in the configuration to avoid directory-related issues. The integration allows Claude to route queries to the APS toolkit, with results formatted back for Claude to present to the user.

How to install

Prerequisites:

Python 3.11 or higher
access to APS credentials for Autodesk APS/ACC
network access to the APS services

Option A: Using uv (recommended)

Install uv if you don't have it: curl -LsSf https://astral.sh/uv/install.sh | sh
Copy .env.sample to .env and fill in your credentials: cp .env.sample .env
Create and activate a virtual environment: uv venv
On Windows:
.venv\Scripts\activate
On Unix or MacOS:
source .venv/bin/activate
Install dependencies: uv pip install -r requirements.txt
Run the MCP server: python aps_dm_server.py

Additional notes

Tips and troubleshooting:

Ensure all environment variables are correctly set in .env or via the mcp_config env block (OPENAI_API_KEY, APS credentials).
Use absolute paths in Claude Desktop configuration to avoid working directory issues.
If you encounter permission errors on macOS, grant Full Disk Access to Terminal and Claude applications.
For Claude Desktop integration, prefer the direct Python path from your virtual environment to APS scripts for stability.
Check logs at the user’s library or project logs if issues arise, e.g., tail -n 50 -f ~/Library/Logs/Claude/mcp*.log.
When testing manually, activate the virtual environment and run: cd /path/to/your/project; source .venv/bin/activate; python aps_dm_server.py.

Related MCP Servers

mcp-vegalite

MCP server from isaacwasserman/mcp-vegalite-server

github-chat

A Model Context Protocol (MCP) for analyzing and querying GitHub repositories using the GitHub Chat API.

nautex

MCP server for guiding Coding Agents via end-to-end requirements to implementation plan pipeline

pagerduty

PagerDuty's official local MCP (Model Context Protocol) server which provides tools to interact with your PagerDuty account directly from your MCP-enabled client.

futu-stock

mcp server for futuniuniu stock

mcp -boilerplate

Boilerplate using one of the 'better' ways to build MCP Servers. Written using FastMCP

aps