Auxen

auxen-ai/auxen-mcp

Connects Claude to Auxen's pay-per-minute GPU provisioning API over StreamableHTTP. You get six tools: list available models (Llama, Qwen, Mistral, Gemma, Phi), provision a new dedicated instance, destroy it, check status and endpoints, read your balance, and list everything running on your account. Authentication works via OAuth 2.1 with PKCE or direct API keys. Each provisioned instance gives you a private endpoint with its own API key, billed by the minute with no shared infrastructure. Useful when you need an agent to spin up model capacity on demand rather than hardcoding inference providers, or when prototyping multi-model pipelines where instance lifetime matters.

tools: 6
transport: HTTP
last updated: Oct 25, 2026

View on GitHub

Tools

6 tools

Public tool metadata for what this MCP can expose to an agent.

auxen_list_modelsList available AI models that can be deployed on Auxen. Filter by size_group to narrow to a tier (small/medium/large/xl).1 params

List available AI models that can be deployed on Auxen. Filter by size_group to narrow to a tier (small/medium/large/xl).

Parameters* required

size_groupstring

Filter by model size.one of small · medium · large · xl

auxen_provision_modelProvision a private AI model instance. Spends money — subscription instances add a Stripe line item; on-demand instances start drawing down USD credits. Returns instance_id; poll auxen_get_instance_status until status is 'running' before making inference calls. Use 'subscripti...4 params

Provision a private AI model instance. Spends money — subscription instances add a Stripe line item; on-demand instances start drawing down USD credits. Returns instance_id; poll auxen_get_instance_status until status is 'running' before making inference calls. Use 'subscripti...

Parameters* required

billingstring

one of subscription · on_demand

labelstring

Human-readable label.

modelstring

Model id from auxen_list_models.

webhook_urlstring

URL to receive instance.ready callback.

auxen_get_instance_statusGet the current status, endpoint, and api_key of a provisioned instance. Poll until status='running' before making inference calls.1 params

Get the current status, endpoint, and api_key of a provisioned instance. Poll until status='running' before making inference calls.

Parameters* required

instance_idstring

inst_xxxxxxxxxxxx from provision.

auxen_list_instancesList all instances for this account.1 params

List all instances for this account.

Parameters* required

statusstring

one of provisioning · running · error · destroyed

auxen_destroy_instanceDestroy an instance and stop billing immediately. Cannot be undone — the instance's endpoint and api_key are permanently invalidated.1 params

Destroy an instance and stop billing immediately. Cannot be undone — the instance's endpoint and api_key are permanently invalidated.

Parameters* required

instance_idstring

auxen_get_balanceGet the account's billing snapshot — USD credit balance for on-demand, count and total of active subscriptions.

Get the account's billing snapshot — USD credit balance for on-demand, count and total of active subscriptions.

No parameter schema in public metadata yet.

Readme

Auxen MCP Server

This is the public manifest repo for the Auxen MCP (Model Context Protocol) server. The server itself runs at https://api.auxen.ai/mcp — this repo exists so registries (Smithery, Glama, the official MCP registry) have a canonical place to read metadata from.

Connect

The Auxen MCP server is a remote, StreamableHTTP server. Add it to your MCP client by URL:

https://api.auxen.ai/mcp

Authentication uses OAuth 2.1 + PKCE (recommended for browser-based clients) or a direct Auxen API key (auxen_live_* / auxen_test_*) sent as Authorization: Bearer <key>.

OAuth flow

The discovery metadata is at:

https://api.auxen.ai/.well-known/oauth-authorization-server (RFC 8414)
https://api.auxen.ai/.well-known/oauth-protected-resource (RFC 9728)

View the full README on GitHub

Details

Repository: github.com/auxen-ai/auxen-mcp
Website: auxen.ai
Category: Automation & Workflows
Transport: HTTP
Registry: MCP registry, active

Related Automation & Workflows MCP servers

View all

Mcp Serverai.meetlark/mcp-serverAgent-first meeting schedule polls for humans and agents. Create polls, vote, find times.0stars

Amalgixamalgix-io/amalgixCross-model evidence pipeline for financial filings & contracts. x402 pay-per-call.0stars

Cannon Studioapp.cannonstudio/cannon-studioPublic Cannon Studio MCP for product, pricing, workflow, model, and API answers.0stars

Kreatixabrahimceylan/kreatix-mcpSchedule and publish posts to Instagram, TikTok, YouTube, Facebook, X, LinkedIn and Pinterest.0stars

Agenticbudgetrouter Mcpclauxel/agentic-budget-router-mcpAgentic workflow budget approvals with usage receipts.0stars

RecallChecker — Vehicle Safety Recallsollo12-prog/recallcheckerCheck U.S. NHTSA vehicle safety recall campaigns by make, model, and year. Live official data.0stars