Auxen MCP
OfficialRegionGlobal
/About Auxen MCP
Auxen is a service that provisions private, dedicated GPU instances running open-source models such as Llama 3.1, Qwen 2.5, Mistral, Gemma 2, and Phi-3. Each instance is fully private, with no shared inference or third-party routing, billed pay-per-minute without subscriptions.
This MCP server exposes Auxen's core account and provisioning operations to AI agents and MCP clients.
AI-generated listing based on the project's public information. It may contain errors: check the original source.
/How to use Auxen MCP
List the models available on Auxen, filtered by size
Check the status and endpoint of my running model instances
Show my current USD credit balance and active subscriptions
Provision a new private instance of Llama 3.1 on my account
Destroy an instance I no longer need
/Auxen MCP tools
What your assistant can call once connected.
| Tool | What it does |
|---|---|
| auxen list models | List available models, optionally filtered by size. Read-only. |
| auxen get instance status | Get status, endpoint, and API key for a model instance. Read-only. |
| auxen list instances | List all instances on the account. Read-only. |
| auxen get balance | Read USD credits and active subscriptions on the account. Read-only. |
| auxen provision model | Provision a new model instance, which spends money. Destructive. |
| auxen destroy instance | Destroy an instance. Irreversible. |
/Before you connect Auxen MCP
Do I need a key or an account?
No. It connects without a key.
Which assistants does it work with?
Claude, ChatGPT, Gemini, Grok
Which countries does it work in?
Any country.
