VRAMfarm GPU Cloud

AI 에이전트가 EU 클라우드 GPU를 분 단위로 대여할 수 있습니다. VRAM과 가격별 GPU 모델을 확인하고, PyTorch, ComfyUI, vLLM 또는 자체 Docker 이미지로 서버를 실행한 뒤 SSH 명령어와 앱 링크를 받고 작업이 끝나면 서버를 중지하세요. 실행할 때마다 시간당 최대 EUR 예산이 적용되며, 잔액은 선불입니다.

호스팅형 MCP 서버

npx add-mcp 'https://vramfarm.com/mcp'

Claude Code, Codex, Cursor 등에 설치됩니다

문서

MCP server: let your AI agent rent the GPU

VRAMfarm speaks the Model Context Protocol. Add one address and your API token to Claude Code, Cursor or VS Code, and the agent can choose a card by VRAM and price, launch a server, read its SSH command and app link, and stop it when the job is done. Billing is per minute from your prepaid balance.

Address and token

Endpoint: https://vramfarm.com/mcp (Streamable HTTP). Authorization: Bearer gf_live_…, an API token from dashboard settings. The token can only list machines, launch, check and stop servers: it cannot change your password, keys or payments.

Connect your client

Claude Code

claude mcp add --transport http vramfarm https://vramfarm.com/mcp \
  --header "Authorization: Bearer gf_live_YOUR_TOKEN"

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "vramfarm": {
      "url": "https://vramfarm.com/mcp",
      "headers": {
        "Authorization": "Bearer gf_live_YOUR_TOKEN"
      }
    }
  }
}

VS Code (.vscode/mcp.json)

{
  "servers": {
    "vramfarm": {
      "type": "http",
      "url": "https://vramfarm.com/mcp",
      "headers": {
        "Authorization": "Bearer gf_live_YOUR_TOKEN"
      }
    }
  }
}

Claude Desktop and other stdio clients (via mcp-remote)

{
  "mcpServers": {
    "vramfarm": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://vramfarm.com/mcp",
        "--header",
        "Authorization: Bearer gf_live_YOUR_TOKEN"
      ]
    }
  }
}

What the agent can do

list_gpu_typesEvery GPU model with VRAM, the cheapest price per hour and how many machines are free
list_offersConcrete machines of one model: country, CUDA, disk, network, price
launch_serverRent a machine with a template (PyTorch, ComfyUI, chat, vLLM, text to speech) or your Docker image. Needs max_eur_per_hour, the agent’s budget
get_serverStatus, cost so far, SSH command, Jupyter and app links
list_serversYour running and recent servers
stop_serverStop billing; optionally save /workspace for the next launch
get_accountBalance and how long it lasts

Spending stays under control

  • Every launch carries max_eur_per_hour: a machine above the agent’s budget is refused before anything is rented.
  • The balance is prepaid: an agent can never spend more than you topped up.
  • Billing is per minute after a 15-minute minimum, and idle servers get an email and auto-stop.
  • Revoke the token in the dashboard at any time; the agent loses access at once.

Try asking your agent

  • “Find the cheapest GPU with at least 24 GB under €0.50 an hour and start PyTorch on it.”
  • “Launch an RTX 4090 with ComfyUI and Flux, give me the link, and stop it in an hour.”
  • “Run my training script from GitHub on an A100, watch it over SSH and stop the server when it finishes.”

Frequently asked questions

What is MCP?

The Model Context Protocol is an open standard that lets AI assistants call external tools. Claude, Cursor, VS Code and many other clients support it.

Does it cost extra?

No. You pay only for the servers the agent runs, at the same per-minute prices as in the dashboard.

Can I use the REST API instead?

Yes, the MCP tools are a thin layer over the same <a href="/en/docs/api/">REST API</a> and the same token.