auxen-mcp
by auxen-ai
This is a manifest repository for a remote MCP server that lets an AI assistant manage dedicated GPU instances on the Auxen service. It can list models, check balance and instances, and provision or destroy private instances running open-source language models.
- Stars
- 0
- Licence
- Unclear
- Runs on
- A cloud service
- Setup
- Easy
- Language
- Not stated
- Age
- 174 days
What you can do with it
- Ask an AI assistant to list available open-source models and their sizes
- Provision a private GPU model instance and get its endpoint and API key
- Check your credit balance and destroy instances you no longer need
Make money with it
A freelancer could set up private hosted AI models for clients who have data privacy concerns and charge for setup and management.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Spin up a private model for handling customer data without sharing it with third-party inference services
- Start and stop pay-per-minute model instances through an assistant to keep hosting costs down
Can you use it commercially?
No standard licence detected. Read the licence before using it commercially.
Not legal advice. Read the project's licence file before building a product on it.
Add it to Claude Code
claude mcp add --transport http auxen https://api.auxen.ai/mcp
This one runs on the maker's server, not your computer, so what you send it leaves your machine.
From the official MCP Registry (ai.auxen/auxen). Only connect MCP servers you trust: they can act on your behalf.
Getting it running
Add the remote server URL https://api.auxen.ai/mcp to your MCP client and sign in with OAuth or an Auxen API key.
Follow the official instructions in the project README.
Things to check
- Needs a paid Auxen account with credits
- Provisioning a model spends real money and is triggered by the assistant
- Destroying an instance is irreversible
- The repo has no licence and only holds metadata, not the server code
- Depends on a single commercial hosted service
Checked 01 Nov 2026. Summary drafted by AI from the project's README.