Summary
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.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Tools
Public tool metadata for what this MCP can expose to an agent.
6 tools
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_groupstringFilter by model size.one of
small · medium · large · xlauxen_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
labelstringHuman-readable label.
modelstringModel id from auxen_list_models.
billingstringone of
subscription · on_demandwebhook_urlstringURL 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_idstringinst_xxxxxxxxxxxx from provision.
auxen_list_instancesList all instances for this account.1 params
List all instances for this account.
Parameters* required
statusstringone of
provisioning · running · error · destroyedauxen_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_idstringauxen_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.
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)
Clients that support Dynamic Client Registration (RFC 7591) — including Claude.ai's Connectors Directory — can register themselves automatically. After registration the client redirects the user's browser to https://api.auxen.ai/oauth/authorize, the user logs in to Auxen and approves the connection on https://auxen.ai/oauth/authorize, and the client receives an authorization code that exchanges for an access token at https://api.auxen.ai/oauth/token.
Direct key (programmatic)
For agents that don't go through a browser, generate an auxen_live_* (or auxen_test_*) key at https://auxen.ai/dashboard/api-keys and send it as Authorization: Bearer <key> on every MCP call.
Tools
| Tool | Effect | Hint |
|---|---|---|
auxen_list_models | List available models, optionally filtered by size | read-only |
auxen_get_instance_status | Get status, endpoint, api_key for an instance | read-only |
auxen_list_instances | List all instances on the account | read-only |
auxen_get_balance | Read USD credits + active subscriptions | read-only |
auxen_provision_model | Provision a new model instance — spends money | destructive |
auxen_destroy_instance | Destroy an instance — irreversible | destructive |
What is Auxen?
Auxen provisions private, dedicated GPU instances running open-source models (Llama 3.1, Qwen 2.5, Mistral, Gemma 2, Phi-3). Each instance is fully private — no shared inference, no third-party routing. Pay-per-minute billing, no subscriptions.
For the human-facing documentation:
- Website: https://auxen.ai
- Architecture explainer: https://auxen.ai/architecture
- Agent reference: https://auxen.ai/agent-reference.md
- Concise reference for LLMs: https://auxen.ai/llms.txt
- OpenAPI 3.1 spec: https://api.auxen.ai/openapi.json
Support
- Email: hello@auxen.ai
- Status: https://status.auxen.ai
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →