Cloud Services

gpu.nz

Provides tools for searching rentable GPU cloud servers, retrieving offer details, listing AI/ML environment templates, and estimating model VRAM requirements.

1 endpoint16 known toolsFirst detected October 20, 2026Last detected October 20, 2026

ENDPOINT 1

https://gpu.nz/mcp

No auth detected

MCP server metadata

Name: gpu.nz
Version: 1.0.0

Capabilities

tools.listChanged

Server instructions

gpu.nz rents cloud GPU servers (RTX 3060 … H100, H200, B200) billed by the minute, paid in rubles or dollars. Without a key you can browse: list_gpu_models, search_offers, get_offer, list_templates, estimate_vram. Renting and managing servers needs an API key in the Authorization header (Bearer gpz_…); the user creates one at https://gpu.nz/console/keys. Money: market prices are rubles per hour for the whole server (price_rub_h); price_usd_h is the same at today's rate. A running server is billed every minute; a stopped one only pays for its disk; destroy frees it entirely. Always tell the user the hourly price and get their explicit confirmation before create_instance, start_instance or destroy_instance. Top-ups happen in the browser: give the user the link from topup_link.

Known tools 16

list_gpu_models

GPU models available on gpu.

Inferred read-only

search_offers

Search rentable GPU servers (offers) with live prices.

Inferred read-only

get_offer

Details and the current price of one offer by id (from search_offers).

Inferred read-only

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.

Inferred read-only

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.

Inferred read-only

get_account

The signed-in account and its balance, hourly burn and runway.

Inferred read-only

list_instances

Your rented servers with status, GPU, price and SSH command.

Potential side effects

get_instance

Status, SSH command, app URLs (ComfyUI, Jupyter, chat…), price and cost so far of one server.

Potential side effects

create_instance

Rents the server of an offer and starts it with a template.

Inferred read-only

stop_instance

Stops a running server: the GPU is released and billing drops to the disk only.

Inferred read-only

start_instance

Starts a stopped server again; GPU billing resumes.

Inferred read-only

destroy_instance

Destroys a server and deletes its disk for good; billing stops completely.

Inferred read-only

get_instance_logs

The last lines of a server's container log: boot progress, app start-up, errors.

Inferred read-only

list_ssh_keys

SSH public keys on the account; they are installed on new servers.

Inferred read-only

add_ssh_key

Adds an SSH public key (a line from a .

Inferred read-only

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.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.gpu-nz]
url = "https://gpu.nz/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "gpu-nz": {
      "type": "http",
      "url": "https://gpu.nz/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: gpu-nz
Remote MCP URL: https://gpu.nz/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "gpu-nz": {
      "url": "https://gpu.nz/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "gpu-nz": {
      "type": "http",
      "url": "https://gpu.nz/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "gpu-nz",
  "transport": "streamable-http",
  "url": "https://gpu.nz/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.