Skip to content
Аренда GPU-серверов и видеокарт logo

Аренда GPU-серверов и видеокарт MCP server

Which MCP servers are Аренда GPU-серверов и видеокарт's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-28

← Back to Аренда GPU-серверов и видеокарт

Whose server it is
  • Registry namenz.gpu/gpu-cloudverified in the MCP registry

The registry name sits under gpu.nz. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools16
  • Server calls itselfgpu.nz
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 709 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 6 of the 7 days it takes to judge reliability.

Once connected

  • For "run Ollama or vLLM chat models on rented GPUs", the likely first call is list_gpu_models.
  • create_instance, add_ssh_key change data without a sign-in: anyone with the address can call them.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 6, the first on 2026-10-28
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
  • Use1 GitHub stars
  • Answeredmeasuring6 of the 7 daily checks it takes to print a share
  • Median first answer785 ms
  • Space in an agent's context≈ 2,360 tokensthe definitions of all its tools (16), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 16 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • not sure · generate images with ComfyUI or Stable Diffusion WebUI
  • can do · run Ollama or vLLM chat models on rented GPUs
  • not sure · fine-tune SDXL and Flux models with Kohya SS

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

  • Tools that change data, on a server that answers without a sign-in: create_instance, add_ssh_key

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers16 tools · read 2026-10-28
  • 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.

  • 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.

  • get_offer

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

  • 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…

  • 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…

  • get_account

    The signed-in account and its balance, hourly burn and runway. Needs a key with user:read and billing:read.

  • list_instances

    Your rented servers with status, GPU, price and SSH command. Needs instances:read.

  • 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).

  • 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…

  • 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…

  • start_instance

    Starts a stopped server again; GPU billing resumes. Confirm with the user. Needs instances:write.

  • destroy_instance

    Destroys a server and deletes its disk for good; billing stops completely. Irreversible: confirm with the user. Needs instances:write.

  • get_instance_logs

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

  • list_ssh_keys

    SSH public keys on the account; they are installed on new servers. Needs user:read.

  • add_ssh_key

    Adds an SSH public key (a line from a .pub file) to the account. Needs user:write.

  • 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.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

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

Add it

Claude Code, in a terminal

claude mcp add --transport http gpu https://gpu.nz/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://gpu.nz/mcp as a custom connector in the settings.

Also shipped through: oci

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.