MCP server

Qwen38 Free Gateway

io.github.khs0927/qwen38-free-gateway

Checked 28 Oct 2026, 09:03 UTC · Connected to it and listed its tools

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

Website

At a glance

Type

MCP server

Publisher

Not verified

Status

Working at last check

Tools

7

Token cost

About 345 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

28 Oct 2026, 09:03 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http qwen38-free-gateway https://api-v2.appdeploy.ai/app/qwen3-8-free-gateway-n995yy/api/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.qwen38-free-gateway]
url = "https://api-v2.appdeploy.ai/app/qwen3-8-free-gateway-n995yy/api/mcp"

Gemini CLI

{"mcpServers":{"qwen38-free-gateway":{"httpUrl":"https://api-v2.appdeploy.ai/app/qwen3-8-free-gateway-n995yy/api/mcp"}}}

Cursor

{"mcpServers":{"qwen38-free-gateway":{"url":"https://api-v2.appdeploy.ai/app/qwen3-8-free-gateway-n995yy/api/mcp"}}}

VS Code

{"servers":{"qwen38-free-gateway":{"type":"http","url":"https://api-v2.appdeploy.ai/app/qwen3-8-free-gateway-n995yy/api/mcp"}}}

Antigravity

agy mcp add qwen38-free-gateway https://api-v2.appdeploy.ai/app/qwen3-8-free-gateway-n995yy/api/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"qwen38-free-gateway","server_url":"https://api-v2.appdeploy.ai/app/qwen3-8-free-gateway-n995yy/api/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"qwen38-free-gateway","server_url":"https://api-v2.appdeploy.ai/app/qwen3-8-free-gateway-n995yy/api/mcp"}

Tools

• gateway_health ~38 tokens
  Check both zero-cost Qwen3.8 providers.
• list_models ~38 tokens
  List Qwen models through the active provider.
• provider_candidates ~44 tokens
  Show evaluated HAPI and Hugging Face provider candidates.
• provider_list ~36 tokens
  List configured zero-cost providers.
• provider_probe ~51 tokens
  Run a real routed gateway inference and report the exact-model ZeroGPU fallback state.
• provider_rank ~42 tokens
  Rank the healthy free providers by priority and latency.
• qwen_chat ~96 tokens
  Ask Qwen3.8-27B through H200 with verified exact-model ZeroGPU failover.

Browse

• GitHub tools
• GitHub and code hosting

Related MCP servers

• Qwen3.8 Heretic Chat
  Qwen3.8 27B Heretic GSQ chat on ZeroGPU
• Qwen3.8 Heretic Chat
  Qwen3.8 27B Heretic GSQ chat on ZeroGPU
• Qwen3.8 27B OBLITERATED GGUF
  Qwen3.8 27B GGUF chat on ZeroGPU
• Qwen3.8 OBLITERATED Chat
  Explore Qwen3.8 27B with streaming text chat
• Qwen3.8-27B Chat
  Multimodal chat with Qwen3.8-27B vision-language model
• Qwen3.8-27B OBLITERATED
  Qwen3.8-27B-OBLITERATED chat demo — ZeroGPU, 4-bit NF4
• Qwen3.8-27B Obliterated Demo
  Chat demo of OBLITERATUS/Qwen3.8-27B-OBLITERATED
• Qwen3.8-27B OBLITERATED — Research Chat
  Chat demo for Qwen3.8-27B OBLITERATED on ZeroGPU

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.khs0927/qwen38-free-gateway.svg)](https://aptlynx.net/servers/io.github.khs0927/qwen38-free-gateway)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents