mcpbeat Sign in

Computegpu MCP Server

answering

Computegpu is answering right now. Last checked 1 min ago. 2 installs a week from npm. It exposes 2 tools. Last commit 9 Jun 2026.

Rent cloud GPUs from your agent: live catalogue, deploy, stop, destroy. Per-second billing.

Uptime history 15 hours of history · worst hour 50%
15 hours agonow
50.0%
Uptime 24h
53 of 106 checks
2
Tools
read from the server
217 ms
Response time
average over 24h
2
Installs / week
npm and PyPI

Computegpu does not always answer

Over the last week it answered 50.0% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.

run in your terminal
claude mcp add computegpu --transport http https://mcp.computegpu.com/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "computegpu": {
      "url": "https://mcp.computegpu.com/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.computegpu]
url = "https://mcp.computegpu.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "computegpu": {
      "url": "https://mcp.computegpu.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "computegpu": {
      "url": "https://mcp.computegpu.com/mcp"
    }
  }
}

This one needs environment variables set before it will start: COMPUTEGPU_API_KEY (ComputeGpu API key (gpu_...). Get one with `npx computegpu signup [email protected] my-agent`; the owner verifies a card ($0, no charge) before the first deploy.). The author declared them in the registry entry; get the values from the project itself.

This server publishes 1 more address. The block above uses the one we reach during checks; the full list is under Endpoints below, and the author may intend a particular one for your client.

Available tools 2

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

computegpu
computegpu_get_started
Explains what ComputeGpu is and how to activate this MCP server (no API key on this session yet).
computegpu_signup
Create a ComputeGpu account. Requires the human's email. Returns an API key (shown once) and unlocks all ComputeGpu tools in this session. Before the first deploy the owner verifies a card ($0, no charge). Ask the human for their email before calling.

Endpoints

URLTransportStateLatencyChecked
https://mcp.computegpu.com/mcp streamable-http answering 217 ms 1 min ago
https://mcp.computegpu.com/sse sse answering 163 ms 1 min ago

Alternatives to Computegpu

same job, measured the same way
Ployz
by ployz

Deploy apps, databases and previews to your own servers. Run Ployz Cloud from your agent.

answering
CloudeIDE
by cloudeide

Deploy from your terminal, and give an AI coding agent the same abilities over MCP.

32 installs/wk local only
PreviewSend
by previewsend

Deploy a built website from your coding agent and share one client review link.

answering
CPZAI
by cpz-lab-mcp

Build, backtest, and deploy quantitative trading strategies from your AI agent.

answering
Unlocalhost
by info-arnav

Deploy localhost to a private, authenticated link from your AI coding agent.

35 installs/wk local only
Swigs Cloud
by swigs

Deploy and manage websites and apps on Swiss hosting, with HTTPS, from your AI agent.

answering
nyxory
by nyxory

Agent-to-agent cloud service: deploys and runs your apps and services — domains, logs, real status.

46 installs/wk answering
P
PreviewDrop
by previewdrop

Deploy any Git branch to a live HTTPS preview URL from your agent. No Dockerfile required.

41 installs/wk local only

Computegpu — questions

Answers built from our own checks of this server.

What can Computegpu do?
It exposes 2 tools, read directly from the server on our last check. Among them: computegpu_get_started, computegpu_signup. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Computegpu working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 53 of 106 checks got a reply (50.0%), average response time 217 ms. The bar chart above shows every period we have measured.
How do I connect Computegpu?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Computegpu need an API key?
No. Computegpu completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 2 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Computegpu?
It answers our handshake in 217 ms on average, which is faster than 57% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use Computegpu?
The npm package computegpu was installed 2 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Computegpu open source?
We cannot say either way: written in JavaScript, 1 stars on GitHub and 1 open issue, but we could not determine the licence, and without one the code is not open source by default.