VRAMfarm GPU Cloud

Down since Nov 13 Security A

com.vramfarm/gpu-cloudv1.0.1 Domain verified

Rent EU cloud GPUs per minute: pick a card by VRAM and price, launch, get SSH, stop.

Cloud & DevOps

Watch Website

Registry entry

Open in the registry

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-11-12T12:30:58.188264Z",
      "publishedAt": "2026-11-12T12:30:58.188264Z",
      "statusChangedAt": "2026-11-12T12:30:58.188264Z"
    }
  },
  "server": {
    "name": "com.vramfarm/gpu-cloud",
    "icons": [
      {
        "src": "https://vramfarm.com/icon-512.png",
        "sizes": [
          "512x512"
        ],
        "mimeType": "image/png"
      },
      {
        "src": "https://vramfarm.com/icon-192.png",
        "sizes": [
          "192x192"
        ],
        "mimeType": "image/png"
      }
    ],
    "title": "VRAMfarm GPU Cloud",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "remotes": [
      {
        "url": "https://vramfarm.com/mcp",
        "type": "streamable-http",
        "headers": [
          {
            "name": "Authorization",
            "isSecret": true,
            "isRequired": true,
            "description": "Bearer gf_live_… API token from https://vramfarm.com/en/dashboard/#settings/tokens"
          }
        ]
      }
    ],
    "version": "1.0.1",
    "websiteUrl": "https://vramfarm.com/en/docs/mcp/",
    "description": "Rent EU cloud GPUs per minute: pick a card by VRAM and price, launch, get SSH, stop."
  }
}

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://vramfarm.com/mcp

Authorization (required)

Bearer gf_live_… API token from https://vramfarm.com/en/dashboard/#settings/tokens

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

get_account Read-only

Balance in EUR, how long it lasts at the current spend, whether an SSH key is set, and limits.

This tool takes no arguments.

Try it

Call this server's tools from your browser. Nothing to install.

https://vramfarm.com/mcp

Authorization (required)

Bearer gf_live_… API token from https://vramfarm.com/en/dashboard/#settings/tokens

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

get_account Read-only

Balance in EUR, how long it lasts at the current spend, whether an SSH key is set, and limits.

This tool takes no arguments.

Tools (7)

Tool list last changed Nov 12, 2026.

get_account

Balance in EUR, how long it lasts at the current spend, whether an SSH key is set, and limits.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

get_server

One server: status (provisioning, running, stopped), what it is doing now, cost so far, and once running the access: SSH command, Jupyter link with token, app URL.

read-only

Argument	Type	Description
id*	integer	Server id, as returned by launch_server or list_servers

Input schema (JSON)

{
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "integer",
      "description": "Server id, as returned by launch_server or list_servers"
    }
  },
  "additionalProperties": false
}

launch_server

Rents a GPU machine and starts a template or a Docker image on it. Costs money from the prepaid balance, billed per minute while running (minimum 15 minutes). Returns at once with the server id; the server is ready in 2–5 minutes (8–15 with a custom image). Refuses machines priced above max_eur_per_hour.

Argument	Type	Description
cmd	string	Start command for template custom
gpu*	string	GPU model code, e.g. rtx-4090 (see list_gpu_types)
disk	integer	Disk in GB (raised to the template minimum)
count	integer	Number of cards, default 1
image	string	Docker image for template custom, as in docker pull
offer_id	integer	Exact machine id from list_offers (optional)
template	string	What to run; default pytorch
max_eur_per_hour*	number	Your budget: the most this server may cost per hour, in EUR, for all cards together
restore_workspace	boolean

list_gpu_types

One row per GPU model and card count: the cheapest reliable machine, its price in EUR per hour, VRAM per card and how many are available. Start here to choose a GPU.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

list_offers

Concrete machines of one GPU model, cheapest first (up to 10), with country, CUDA, disk, network and price. Use the id as offer_id in launch_server to pick an exact machine.

read-only

Argument	Type	Description
gpu*	string	GPU model code, e.g. rtx-4090, a100, h100 (see list_gpu_types)
count	integer	Cards per machine

Input schema (JSON)

{
  "type": "object",
  "required": [
    "gpu"
  ],
  "properties": {
    "gpu": {
      "type": "string",
      "description": "GPU model code, e.g. rtx-4090, a100, h100 (see list_gpu_types)"
    },
    "count": {
      "enum": [
        1,
        2,
        4,
        8
      ],
      "type": "integer",
      "description": "Cards per machine"
    }
  },
  "additionalProperties": false
}

list_servers

Your servers, newest first: running, starting and stopped in the last 7 days, with status, price and access.

read-only

Argument	Type	Description
status	string	Only servers in this state: provisioning (starting), running or stopped (last 7 days); omit for all

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "status": {
      "enum": [
        "provisioning",
        "running",
        "stopped"
      ],
      "type": "string",
      "description": "Only servers in this state: provisioning (starting), running or stopped (last 7 days); omit for all"
    }
  },
  "additionalProperties": false
}

stop_server

Stops a server and its billing. The disk is wiped; with save_workspace true the /workspace folder is saved first (storage is billed per GB-month) and comes back on the next launch.

destructive

Argument	Type	Description
id*	integer	Server id to stop, as returned by launch_server or list_servers
save_workspace	boolean	Save /workspace before stopping, default false

Input schema (JSON)

{
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "integer",
      "description": "Server id to stop, as returned by launch_server or list_servers"
    },
    "save_workspace": {
      "type": "boolean",
      "description": "Save /workspace before stopping, default false"
    }
  },
  "additionalProperties": false
}

VRAMfarm GPU Cloud

Registry entry

Try it

get_account Read-only

VRAMfarm GPU Cloud

Registry entry

Try it

get_account Read-only

Install

Tools (7)

Security checkA100/100

Tool changes