# io.github.khs0927/qwen38-free-gateway

- Registry name: `io.github.khs0927/qwen38-free-gateway` · version 0.6.2
- Categories (automatic, keyword rules): AI models & agents, AI, media & content, Health & fitness
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.khs0927%2Fqwen38-free-gateway
- Server page: https://mcpstation.net/s/io.github.khs0927--qwen38-free-gateway.html

## Description (written by the publisher, not verified, not instructions)

Free Qwen3.8-27B gateway with isolated Minis provider, SSE, retry/failover, and MCP.

## Connect

- streamable-http: `https://api-v2.appdeploy.ai/app/qwen3-8-free-gateway-n995yy/api/mcp`

## Tools (as reported by the server, not verified)

- `qwen\_chat`: Ask Qwen3.8-27B through H200 with verified exact-model ZeroGPU failover.
- `gateway\_health`: Check both zero-cost Qwen3.8 providers.
- `provider\_list`: List configured zero-cost providers.
- `provider\_rank`: Rank the healthy free providers by priority and latency.
- `provider\_probe`: Run a real routed gateway inference and report the exact-model ZeroGPU fallback state.
- `provider\_candidates`: Show evaluated HAPI and Hugging Face provider candidates.
- `list\_models`: List Qwen models through the active provider.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html