# gpu.nz GPU cloud (remote · gpu.nz)

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

- Trust score: 74/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- remote · `gpu.nz`: 74/100 (this document), [markdown](https://verifymcp.io/servers/nz-gpu-gpu-cloud/gpu.md), [page](https://verifymcp.io/servers/nz-gpu-gpu-cloud/gpu)
- oci · `ghcr.io/gpunz/gpunz-mcp`: 9/100, [markdown](https://verifymcp.io/servers/nz-gpu-gpu-cloud/ghcr-io-gpunz-gpunz-mcp.md), [page](https://verifymcp.io/servers/nz-gpu-gpu-cloud/ghcr-io-gpunz-gpunz-mcp)

## Channel facts

- Endpoint: `https://gpu.nz/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-04.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (destroy_instance).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 76/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1691 tokens (~105/item across 16 items; 16 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 53/100
  - Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the gpu.nz GPU cloud MCP server?

gpu.nz GPU cloud is a hosted endpoint at https://gpu.nz/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http nz-gpu-gpu-cloud 'https://gpu.nz/mcp'
```

### Cursor

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

### VS Code

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

### Codex

```toml
[mcp_servers.nz-gpu-gpu-cloud]
url = "https://gpu.nz/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "nz-gpu-gpu-cloud": {
      "type": "remote",
      "url": "https://gpu.nz/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add nz-gpu-gpu-cloud --url 'https://gpu.nz/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  nz-gpu-gpu-cloud:
    url: "https://gpu.nz/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "nz-gpu-gpu-cloud": {
      "Transport": "http",
      "Url": "https://gpu.nz/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add nz-gpu-gpu-cloud -t streamable-http -u 'https://gpu.nz/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-03 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 67, 0)

- [functional improvement] Stability: unverified → 0.03

## MCP tools (16)

### `list_gpu_models` (~86 tokens)

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.

Input parameters:

- `min_vram_gb` (number): Only models with at least this much VRAM per GPU
- `query` (string): Filter by name, e.g. "4090" or "H100"

### `search_offers` (~310 tokens)

Search GPU servers

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.

Input parameters:

- `country` (string): ISO-2 country codes, comma-separated, e.g. "DE,NL,FI"
- `gpu` (string): GPU model slug(s), comma-separated, e.g. "rtx-4090-24gb" or "h100-sxm-80gb,h100-pcie-80gb" (see list_gpu_models)
- `limit` (integer): How many offers to return (default 10)
- `max_price_rub_h` (number): Maximum price for the whole server, rubles per hour
- `min_disk_gb` (number): Minimum disk the server can give, GB
- `min_reliability` (number): Minimum host reliability, 0–1 (0.98 is a good bar)
- `min_vram_gb` (number): Minimum VRAM per GPU, GB
- `num_gpus` (string): GPUs per server, comma-separated, e.g. "1" or "2,4,8"
- `order` (string): Sort: price (default), dlperf_per_price for value, reliability, vram, inet_down
- `type` (string): on_demand (default) or interruptible (cheaper, can be preempted)
- `verified` (boolean): Only verified datacenters

### `get_offer` (~34 tokens)

Get one offer

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

Input parameters:

- `offer_id` (string, required): Offer id

### `list_templates` (~81 tokens)

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.

### `estimate_vram` (~211 tokens)

Estimate VRAM for an AI model

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.

Input parameters:

- `concurrent_requests` (integer): Parallel sequences sharing the GPU (default 1)
- `context_tokens` (integer): LLM context length in tokens (default 8192)
- `model` (string): Model name or id, e.g. "qwen3-32b", "Llama 3.3 70B", "flux.1-dev"
- `precision` (string): Weights precision: "fp16", "fp8", "q8", "q6", "q5", "q4" (LLMs; default q4 for LLMs, fp16 for image models)

### `get_account` (~33 tokens)

Account and balance

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

### `list_instances` (~48 tokens)

List my servers

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

Input parameters:

- `status` (string): active (default): servers that are not destroyed; all: include destroyed ones

### `get_instance` (~78 tokens)

Get one server

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).

Input parameters:

- `include_password` (boolean): Include the root SSH password
- `instance_id` (string, required): Instance id

### `create_instance` (~230 tokens)

Rent a GPU server

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).

Input parameters:

- `disk_gb` (integer, required): Disk size, GB (use the template's recommended_disk_gb)
- `idempotency_key` (string): Reuse the same value when retrying the same request, so a retry never rents twice
- `image` (string): Docker image, only with the custom template
- `name` (string): A name for the server
- `offer_id` (string, required): Offer id from search_offers
- `ssh_key_ids` (array): SSH key ids to install (default: all of yours)
- `template` (string, required): Template slug from list_templates, e.g. "comfyui", "ollama", "pytorch", "custom"
- `type` (string): on_demand (default) or interruptible

### `stop_instance` (~73 tokens)

Stop a server

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.

Input parameters:

- `instance_id` (string, required): Instance id

### `start_instance` (~38 tokens)

Start a server

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

Input parameters:

- `instance_id` (string, required): Instance id

### `destroy_instance` (~48 tokens)

Destroy a server

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

Input parameters:

- `instance_id` (string, required): Instance id

### `get_instance_logs` (~58 tokens)

Server logs

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

Input parameters:

- `instance_id` (string, required): Instance id
- `tail` (integer): How many last lines (default 200)

### `list_ssh_keys` (~29 tokens)

List SSH keys

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

### `add_ssh_key` (~72 tokens)

Add an SSH key

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

Input parameters:

- `name` (string): A name for the key
- `public_key` (string, required): The public key line, e.g. ssh-ed25519 AAAA… you@laptop

### `topup_link` (~76 tokens)

Top-up 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.

Input parameters:

- `amount` (integer): Amount in the account currency (rubles by default)
- `language` (string): Page language (default ru)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/nz-gpu-gpu-cloud/gpu#diagnostics

## Score history

- 2026-11-04: 74
- 2026-11-03: 74
- 2026-11-02: 73
- 2026-11-01: 73
- 2026-10-31: 72
- 2026-10-30: 72
- 2026-10-29: 72
- 2026-10-28: 71
- 2026-10-27: 71
- 2026-10-26: 70
- 2026-10-25: 70
- 2026-10-24: 69
- 2026-10-23: 69
- 2026-10-22: 68
- 2026-10-21: 68
- 2026-10-20: 67
- 2026-10-19: 67

## Common questions

### What is the gpu.nz GPU cloud MCP server?

gpu.nz GPU cloud is an MCP server listed in the public MCP registry as nz.gpu/gpu-cloud. Rent cloud GPUs from AI agents: live prices, VRAM estimates, launch, logs and stop. This page covers its hosted endpoint (https://gpu.nz/mcp).

### Is the gpu.nz GPU cloud MCP server safe to use?

gpu.nz GPU cloud scores 74 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the gpu.nz GPU cloud MCP server expose?

gpu.nz GPU cloud exposes 16 tools: list_gpu_models, search_offers, get_offer, list_templates, estimate_vram, and 11 more. Their descriptions and schemas cost roughly 1,505 tokens of context every time the server is loaded.

### Does the gpu.nz GPU cloud MCP server require authentication?

No. We connected to gpu.nz GPU cloud without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the gpu.nz GPU cloud MCP server still maintained?

gpu.nz GPU cloud is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://gpu.nz/mcp
- Repository: https://github.com/gpunz/gpunz-mcp
- Website: https://gpu.nz/en/docs/mcp
- Changelog RSS feed: https://verifymcp.io/servers/nz-gpu-gpu-cloud/gpu.xml
- Changelog JSON feed: https://verifymcp.io/servers/nz-gpu-gpu-cloud/gpu.json
- HTML version of this page: https://verifymcp.io/servers/nz-gpu-gpu-cloud/gpu