{
  "markdown": "# Auxen MCP Server\n\nThis 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.\n\n## Connect\n\nThe Auxen MCP server is a **remote, StreamableHTTP** server. Add it to your MCP client by URL:\n\n```\nhttps://api.auxen.ai/mcp\n```\n\nAuthentication 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>`.\n\n### OAuth flow\n\nThe discovery metadata is at:\n\n- `https://api.auxen.ai/.well-known/oauth-authorization-server` (RFC 8414)\n- `https://api.auxen.ai/.well-known/oauth-protected-resource` (RFC 9728)\n\nClients that support [Dynamic Client Registration (RFC 7591)](https://datatracker.ietf.org/doc/html/rfc7591) — 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`.\n\n### Direct key (programmatic)\n\nFor 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.\n\n## Tools\n\n| Tool | Effect | Hint |\n|------|--------|------|\n| `auxen_list_models` | List available models, optionally filtered by size | read-only |\n| `auxen_get_instance_status` | Get status, endpoint, api_key for an instance | read-only |\n| `auxen_list_instances` | List all instances on the account | read-only |\n| `auxen_get_balance` | Read USD credits + active subscriptions | read-only |\n| `auxen_provision_model` | Provision a new model instance — **spends money** | destructive |\n| `auxen_destroy_instance` | Destroy an instance — **irreversible** | destructive |\n\n## What is Auxen?\n\nAuxen 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.\n\nFor the human-facing documentation:\n\n- Website: <https://auxen.ai>\n- Architecture explainer: <https://auxen.ai/architecture>\n- Agent reference: <https://auxen.ai/agent-reference.md>\n- Concise reference for LLMs: <https://auxen.ai/llms.txt>\n- OpenAPI 3.1 spec: <https://api.auxen.ai/openapi.json>\n\n## Support\n\n- Email: <hello@auxen.ai>\n- Status: <https://status.auxen.ai>\n",
  "bytes": 2757,
  "sha": "37328befa05fb997e97a68d7e431411a70e95f3813e1ede16c0e2722ca73f721",
  "repo_slug": "auxen-ai/auxen-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_auxen_auxen_87778040/readme"
}