GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
作者提供的说明(英文原文)
Rent cloud GPUs from AI agents: live prices, VRAM estimates, launch, logs and stop.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
GPUNZ_API_KEY, Authorization标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"gpu-cloud": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GPUNZ_API_KEY",
"ghcr.io/gpunz/gpunz-mcp:1.0.0"
],
"env": {
"GPUNZ_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add --transport http gpu-cloud https://gpu.nz/mcp --header 'Authorization: your-value'claude mcp add gpu-cloud --env GPUNZ_API_KEY=your-value -- docker run -i --rm -e GPUNZ_API_KEY ghcr.io/gpunz/gpunz-mcp:1.0.0运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"gpu-cloud": {
"url": "https://gpu.nz/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"gpu-cloud": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GPUNZ_API_KEY",
"ghcr.io/gpunz/gpunz-mcp:1.0.0"
],
"env": {
"GPUNZ_API_KEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"gpu-cloud": {
"type": "http",
"url": "https://gpu.nz/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"gpu-cloud": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GPUNZ_API_KEY",
"ghcr.io/gpunz/gpunz-mcp:1.0.0"
],
"env": {
"GPUNZ_API_KEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
你的选择通过 Cookie 保存在这台设备上,无需账户。
Authorization 机密 HTTP header这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
工具名称和描述与服务器在 2026年11月7日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
list_gpu_modelsGPU models available on gpu.nz right now with VRAM, class and the cheapest hourly price per GPU. Use it to pick a gpu_slug for search_offers.
search_offersSearch rentable GPU servers (offers) with live prices. Returns the cheapest matches first unless `order` says otherwise. Each result has an offer id for create_instance.
get_offerDetails and the current price of one offer by id (from search_offers).
list_templatesReady environments a server can start with: ComfyUI, Stable Diffusion Forge, Ollama + Open WebUI, vLLM, Jupyter/PyTorch, Kohya, FluxGym, Unsloth, chats with preloaded models, plain Ubuntu + CUDA, or a custom Docker image. Pass `slug` as `template` to create_instance.
estimate_vramHow much GPU memory an AI model needs (LLMs such as Qwen, DeepSeek, Llama, Gemma, GPT-OSS; image and video models such as FLUX, SDXL, Wan) at a given precision and context length, and which GPUs on gpu.nz fit it with their current price. Call without `model` to list the known mod
get_accountThe signed-in account and its balance, hourly burn and runway. Needs a key with user:read and billing:read.
list_instancesYour rented servers with status, GPU, price and SSH command. Needs instances:read.
get_instanceStatus, SSH command, app URLs (ComfyUI, Jupyter, chat…), price and cost so far of one server. The root password is left out unless include_password is true (your SSH keys are installed on every server).
create_instanceRents the server of an offer and starts it with a template. Billing starts right away and runs every minute until you stop or destroy it. Confirm the price with the user first. Needs instances:write. The response has the instance id; poll get_instance until status is running (usu
stop_instanceStops a running server: the GPU is released and billing drops to the disk only. Data on the disk is kept and the server can be started again (the GPU may then be taken by someone else; gpu.nz finds a replacement when it is). Needs instances:write.
start_instanceStarts a stopped server again; GPU billing resumes. Confirm with the user. Needs instances:write.
destroy_instanceDestroys a server and deletes its disk for good; billing stops completely. Irreversible: confirm with the user. Needs instances:write.
get_instance_logsThe last lines of a server's container log: boot progress, app start-up, errors. Needs instances:read.
list_ssh_keysSSH public keys on the account; they are installed on new servers. Needs user:read.
add_ssh_keyAdds an SSH public key (a line from a .pub file) to the account. Needs user:write.
topup_linkA link to the balance top-up page (SBP, crypto) for the user to open in a browser; payments never happen through the API. Optionally pre-fills the amount.
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日
注册名称已通过域名 gpu.nz 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
在 581 毫秒内响应(HTTP 200)
无需登录
已读取 16 个工具描述,未发现针对 AI 的隐藏指令
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:GPUNZ_API_KEY, Authorization
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(1.0.0)于19天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:GitHub, Desktop Commander, Cloudflare MCP
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
MCP server for terminal commands, file operations, and process management
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Let Claude, Cursor, Codex and other AI agents rent cloud GPUs: search RTX 4090, A100, H100 and B200 servers with live prices, work out how much VRAM a model needs, launch ComfyUI, Ollama, vLLM or Jupyter, read the logs and stop the server when the job is done. Billed by the minute.
Docs · VRAM calculator · REST API · CLI · Русский
The server is hosted at `https://gpu.nz/mcp` — nothing to install. Browsing GPUs, prices and VRAM estimates works without a key; renting and managing servers needs an API key from gpu.nz/console/keys.
Claude Code
claude mcp add --transport http gpunz https://gpu.nz/mcp \
--header "Authorization: Bearer gpz_…"
Cursor — ~/.cursor/mcp.json
{
"mcpServers": { "gpunz": { "url": "https://gpu.nz/mcp", "headers": { "Authorization": "Bearer gpz_…" } } } }
VS Code — .vscode/mcp.json (asks for the key once and keeps it in secret storage)
{
"servers": { "gpunz": { "type": "http", "url": "https://gpu.nz/mcp", "headers": { "Authorization": "Bearer ${input:gpunz-key}" } } }, "inputs": [{ "type": "promptString", "id": "gpunz-key", "description": "gpu.nz API key", "password": true }] }
Codex CLI
export GPUNZ_API_KEY="gpz_…"
codex mcp add gpunz --url https://gpu.nz/mcp --bearer-token-env-var GPUNZ_API_KEY
Claude Desktop — claude_desktop_config.json, through mcp-remote
{
"mcpServers": { "gpunz": { "command": "npx", "args": ["-y", "mcp-remote", "https://gpu.nz/mcp", "--header", "Authorization:${GPUNZ_AUTH}"], "env": { "GPUNZ_AUTH": "Bearer gpz_…" } } } }
On claude.ai you can add https://gpu.nz/mcp under Connectors without a key: search and estimates work.
For clients that only start local servers, this repository is a small stdio bridge to the hosted server:
# Docker
docker run -i --rm -e GPUNZ_API_KEY="gpz_…" ghcr.io/gpunz/gpunz-mcp
GPUNZ_API_KEY="gpz_…" npx -y github:gpunz/gpunz-mcp
| Variable | |
|---|---|
GPUNZ_API_KEY | API key (gpz_…). Optional: without it only the browsing tools work |
GPUNZ_MCP_URL | Endpoint override, default https://gpu.nz/mcp |
| Tool | What it does | Key scope |
|---|---|---|
list_gpu_models | GPU models in stock: memory, class, cheapest price per hour | — |
search_offers | Servers with live prices; filter by GPU, count, VRAM, price, country, reliability | — |
get_offer | One server and its current price | — |
list_templates | Ready environments: ComfyUI, Forge, Ollama + Open WebUI, vLLM, Jupyter, Kohya, FluxGym, Unsloth, your own Docker image | — |
estimate_vram | VRAM a model needs (Qwen, DeepSeek, Llama, Gemma, GPT-OSS, FLUX, Wan…) at a quantisation and context, and the cheapest GPUs that fit | — |
topup_link | A link to top up the balance in the browser | — |
get_account | Account, balance, hourly spend and runway | user:read, billing:read |
list_instances · get_instance | Your servers: status, SSH command, app URLs, cost so far | instances:read |
get_instance_logs | The last log lines: boot, app start-up, errors | instances:read |
create_instance | Rents a server with a template; billing starts at once | instances:write |
stop_instance · start_instance | Stop (only the disk is billed) and start again | instances:write |
destroy_instance | Destroys a server and its disk | instances:write |
list_ssh_keys · add_ssh_key | SSH keys installed on new servers | user:read / user:write |
create_instance, start_instance and destroy_instance are annotated as consequential, so clients ask you before running them.MCP-сервер gpu.nz подключает аренду видеокарт к ИИ-агентам: Claude, Cursor, Codex и другим. Агент сам найдёт подходящую видеокарту, посчитает видеопамять для модели, арендует сервер с ComfyUI, Ollama или vLLM, прочитает логи и остановит сервер. Адрес: https://gpu.nz/mcp, оплата поминутная, в рублях через СБП или криптой. Документация: gpu.nz/docs/mcp.
MIT. gpu.nz is a GPU cloud billed by the minute; the hosted server and the API are run by gpu.nz.