mcpbeat Sign in

gpu.nz GPU cloud MCP Server

answering

gpu.nz GPU cloud is answering right now. Last checked 14 min ago. It exposes 16 tools. Last commit 21 Oct 2026.

Rent cloud GPUs from AI agents: live prices, VRAM estimates, launch, logs and stop.

Uptime history 7 days of history
7 days agonow
100.0%
Uptime 24h
91 of 91 checks
16
Tools
read from the server
385 ms
Response time
average over 24h
1
Stars
last commit 21 Oct 2026

Nothing serious here today

Today is the operative word: we check gpu.nz GPU cloud every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.

run in your terminal
claude mcp add gpu-cloud --transport http https://gpu.nz/mcp
Settings → Connectors → Add custom connector, then paste this address
https://gpu.nz/mcp
~/.codex/config.toml
[mcp_servers.gpu-cloud]
url = "https://gpu.nz/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "gpu-cloud": {
      "url": "https://gpu.nz/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "gpu-cloud": {
      "type": "http",
      "url": "https://gpu.nz/mcp"
    }
  }
}

Available tools 16

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

instance
create_instance
Rents 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 (usually 1–5 minutes).
get_instance
Status, 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).
get_instance_logs
The last lines of a server's container log: boot progress, app start-up, errors. Needs instances:read.
ssh
add_ssh_key
Adds an SSH public key (a line from a .pub file) to the account. Needs user:write.
list_ssh_keys
SSH public keys on the account; they are installed on new servers. Needs user:read.
account
get_account
The signed-in account and its balance, hourly burn and runway. Needs a key with user:read and billing:read.
destroy
destroy_instance
Destroys a server and deletes its disk for good; billing stops completely. Irreversible: confirm with the user. Needs instances:write.
estimate
estimate_vram
How 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 models.
gpu
list_gpu_models
GPU 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.
instances
list_instances
Your rented servers with status, GPU, price and SSH command. Needs instances:read.
offer
get_offer
Details and the current price of one offer by id (from search_offers).
offers
search_offers
Search 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.
start
start_instance
Starts a stopped server again; GPU billing resumes. Confirm with the user. Needs instances:write.
stop
stop_instance
Stops 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.
templates
list_templates
Ready 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.
topup
topup_link
A 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.

Endpoints

URLTransportStateLatencyChecked
https://gpu.nz/mcp streamable-http answering 467 ms 14 min ago

Alternatives to gpu.nz GPU cloud

same job, measured the same way
LogsLoom
by efim23

Ingest and search LogsLoom logs from coding agents.

16 installs/wk 4 tools answering
Verlon AI MCP
by verlon

Inspect and manage Verlon AI gates, logs, recommendations, and experiments from any MCP client.

43 installs/wk local only
PreviewAPK
by livetaub

Give your AI agent a real cloud Android phone: push APKs, drive it, get screenshots and logs.

answering
Statuser
by statuser-cloud

Monitor services, manage incidents and status pages in Statuser.cloud from your AI assistant.

229 installs/wk answering
New Shopify Stores Radar
by yzf75011-ui

New and pre-launch Shopify stores from public CT logs: RDAP date, niche, country. No PII.

answering
nyxory
by nyxory

Agent-to-agent cloud service: deploys and runs your apps and services — domains, logs, real status.

355 installs/wk answering
Blazingcdn MCP
by blazingcdn

Manage BlazingCDN from AI agents: CDN zones, cache, metrics, domains, cloud storage and video CDN

27 installs/wk local only
Contractor Foreman by Cotlet
by cotlet

Projects, estimates, daily logs and invoices in Contractor Foreman.

296 installs/wk 106 tools answering

gpu.nz GPU cloud — questions

Answers built from our own checks of this server.

What can gpu.nz GPU cloud do?
It exposes 16 tools, read directly from the server on our last check. Among them: add_ssh_key, create_instance, destroy_instance, estimate_vram, get_account, get_instance and 10 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
What is gpu.nz GPU cloud mostly used for?
Its tools cluster around instance and ssh. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is gpu.nz GPU cloud working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 385 ms. The bar chart above shows every period we have measured.
How do I connect gpu.nz GPU cloud?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does gpu.nz GPU cloud need an API key?
No. gpu.nz GPU cloud completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 16 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is gpu.nz GPU cloud?
It answers our handshake in 385 ms on average, which is faster than 38% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is gpu.nz GPU cloud open source?
The code is open source: it is published under the MIT licence, written in JavaScript, 1 stars on GitHub and 1 open issue. The licence covers the code in the repository, not the hosted service at gpu.nz, which runs on its operator's own terms.