Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "gpu-cloud": {
      "type": "http",
      "url": "https://gpu.nz/mcp",
      "headers": {
        "Authorization": "Bearer ${GPU_CLOUD_TOKEN}"
      }
    }
  }
}

claude mcp add --transport http gpu-cloud https://gpu.nz/mcp --header "Authorization: Bearer ${GPU_CLOUD_TOKEN}"

[mcp_servers.gpu-cloud]
url = "https://gpu.nz/mcp"
bearer_token_env_var = "GPU_CLOUD_TOKEN"

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

{
  "mcpServers": {
    "gpu-cloud": {
      "type": "http",
      "url": "https://gpu.nz/mcp",
      "headers": {
        "Authorization": "Bearer ${GPU_CLOUD_TOKEN}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=gpu-cloud&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vZ3B1Lm56L21jcCIsImhlYWRlcnMiOnsiQXV0aG9yaXphdGlvbiI6IkJlYXJlciAke0dQVV9DTE9VRF9UT0tFTn0ifX0%3D"
}

{
  "servers": {
    "gpu-cloud": {
      "type": "http",
      "url": "https://gpu.nz/mcp",
      "headers": {
        "Authorization": "Bearer ${GPU_CLOUD_TOKEN}"
      }
    }
  }
}

{
  "mcpServers": {
    "gpu-cloud": {
      "httpUrl": "https://gpu.nz/mcp",
      "headers": {
        "Authorization": "Bearer ${GPU_CLOUD_TOKEN}"
      }
    }
  }
}

extensions:
  "gpu-cloud":
    enabled: true
    name: "gpu-cloud"
    type: streamable_http
    uri: "https://gpu.nz/mcp"
    headers:
      "Authorization": "Bearer ${GPU_CLOUD_TOKEN}"
    timeout: 300

Placeholders to fill from your own secret store: ${GPU_CLOUD_TOKEN}. The registry never accepts secret values.

Quality 85 / 100new

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene93 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations16 of 16 tools declare readOnlyHint or destructiveHint
warn
tools.directory_hints5 of 16 tools declare all four hints; missing: list_gpu_models (destructiveHint, idempotentHint); get_offer (destructiveHint, idempotentHint); get_account (destructiveHint, idempotentHint); …
pass
tools.token_costabout 2,509 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stabilityn/a · weight 15

n/a
stability.changes, stability.rug_pulltool history recorded for 0 of the 7 days needed

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

16 tools, about 2,509 tokens to load them all · tool set c1b487d0df04 · checked 2026-10-20 03:37 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 95 / 100

provenance85

liveness100

freshness100

hygiene95

+repository +dns-namespace +website +reachable +uptime-100% +updated-0d-ago -unpinned-packages(1)

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://gpu.nz/mcp` streamable-http	none	yes	100%	508 ms	2025-11-25	2026-10-20

package	registry	version	runtime	secrets
`ghcr.io/gpunz/gpunz-mcp:1.0.0`	oci	unpinned	–	`GPUNZ_API_KEY`

Tools (16)

`add_ssh_key`	Adds an SSH public key (a line from a .pub file) to the account. Needs user:write.
`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).
`destroy_instance`destructive	Destroys a server and deletes its disk for good; billing stops completely. Irreversible: confirm with the user. Needs instances:write.
`estimate_vram`read-only	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.
`get_account`read-only	The signed-in account and its balance, hourly burn and runway. Needs a key with user:read and billing:read.
`get_instance`read-only	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`read-only	The last lines of a server's container log: boot progress, app start-up, errors. Needs instances:read.
`get_offer`read-only	Details and the current price of one offer by id (from search_offers).
`list_gpu_models`read-only	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.
`list_instances`read-only	Your rented servers with status, GPU, price and SSH command. Needs instances:read.
`list_ssh_keys`read-only	SSH public keys on the account; they are installed on new servers. Needs user:read.
`list_templates`read-only	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.
`search_offers`read-only	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_instance`	Starts a stopped server again; GPU billing resumes. Confirm with the user. Needs instances:write.
`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.
`topup_link`read-only	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.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "nz.gpu/gpu-cloud",
  "title": "gpu.nz GPU cloud",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://gpu.nz/mcp",
      "type": "streamable-http",
      "headers": [
        {
          "name": "Authorization",
          "isSecret": true,
          "description": "Bearer gpz_… API key from https://gpu.nz/console/keys. Optional: without it only GPU search, prices and VRAM estimates work."
        }
      ]
    }
  ],
  "version": "1.0.0",
  "packages": [
    {
      "transport": {
        "type": "stdio"
      },
      "identifier": "ghcr.io/gpunz/gpunz-mcp:1.0.0",
      "registryType": "oci",
      "environmentVariables": [
        {
          "name": "GPUNZ_API_KEY",
          "isSecret": true,
          "description": "API key (gpz_…) from https://gpu.nz/console/keys. Optional: without it only browsing tools work."
        }
      ]
    }
  ],
  "repository": {
    "url": "https://github.com/gpunz/gpunz-mcp",
    "source": "github"
  },
  "websiteUrl": "https://gpu.nz/en/docs/mcp",
  "description": "Rent cloud GPUs from AI agents: live prices, VRAM estimates, launch, logs and stop."
}