Auxen

auxen.ai
Visit site

Provision private AI model endpoints on dedicated GPUs (Llama, Qwen, Mistral). Pay per minute.

Description

The inference layer agents run themselves. · Deploy a private AI model on a dedicated GPU. Per-minute billing — no token charges, no monthly minimums. OpenAI-compatible endpoint that never changes. · Why not just call a per-token API? · A model youragent runs itself. · The agent lifecyclein three steps · Everything included.Nothing extra.

Installation

Not sure where to start — ask an assistant to walk you through:

Specs

Type MCP server
SectionMCP servers
Pricing free
Platform Command line
Systems cli, api
Hostingcloud
Installmcp
Protocolsmcp
Site languageen
GitHubauxen-ai/auxen-mcp
Launched2026-05-18

Can do

agents api vision reasoning fine-tuning RAG on-premise

Integrations

claude openai Shopify WordPress Vercel langchain Webflow

Platforms

api cli

Protocols

mcp

Tags

agents api vision reasoning RAG fine-tuning on-premise

Social

GitHub

Source code

auxen-ai/auxen-mcp

Found in sources

mcp-registry

Similar in «MCP servers»

ClickHouse
Official ClickHouse MCP server for querying and exploring ClickHouse clusters and chDB.
JustCall MCP Server
JustCall MCP Server enables LLMs and AI agents to make voice calls and send SMS via JustCall APIs.
Octoparse MCP Server
Official Octoparse MCP server for template discovery, cloud tasks, and structured data export.
Parallel Search MCP
The best web search for your AI Agent
Outset
AI-moderated research platform: create and launch studies and query interview results.
io.gainium/gainium-mcp
MCP server for Gainium — manage trading bots, deals, and balances via AI assistants

Submit a site to the catalog

Just send the link — we will work out the rest.

We will review what you send and add it to the catalog if it fits.

Not sure how to implement it? We can help

Tell us about your task — we will pick the tools and suggest where to start.

0 / 5000
Verification code

Fields marked with an asterisk are required. Your data is used only to reply.