What dependencies or runtime does APS MCP Server require?
Python 3.11 or higher, with dependencies listed in `requirements.txt`. Key libraries include aps‑toolkit, mcp, python‑dotenv, and optionally openai.
@kpphillips
基本情報
Simple prototype MCP server integrating Autodesk APIs
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"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"
}
}
}
}Get all available hubs
Get all projects within a hub
Get files in a specific folder of a project
Get version information for a specific item
A minimal MCP server that integrates Autodesk ACC (Autodesk Construction Cloud) APIs via the APS (Autodesk Platform Services) toolkit, acting as a bridge between Claude AI and the Autodesk APS platform. It is intended for users who need to query and manage Autodesk project data through AI assistants.
Clone the repository, copy .env.sample to .env and fill in your Autodesk credentials. Install dependencies using uv or pip, then run python aps_dm_server.py. For use with Claude Desktop, add the server configuration (with absolute paths) to claude_desktop_config.json. Optionally, use with the OpenAI Agents SDK by installing openai and running python main_agent.py.
.env.Python 3.11 or higher, with dependencies listed in `requirements.txt`. Key libraries include aps‑toolkit, mcp, python‑dotenv, and optionally openai.
Credentials are stored in a local `.env` file. All data remains within Autodesk APS/ACC; the server only fetches and relays information without persistent local storage.
It uses the MCP (Model Context Protocol) transport with JSON‑RPC messaging. Authentication is via Autodesk APS credentials configured in the `.env` file.
The README states this is a prototype “as is” with no warranty, for demonstration purposes only. No explicit performance or concurrency limits are documented.
Check configuration JSON syntax, use absolute paths, grant Full Disk Access on macOS (System Preferences → Privacy & Security), and review logs at `~/Library/Logs/Claude/mcp*.log`. Test the server manually by running `python aps_dm_server.py`.

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep
🚀 The fast, Pythonic way to build MCP servers and clients.
コメント