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.
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.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.
claude mcp add computegpu --transport http https://mcp.computegpu.com/mcp
{
"mcpServers": {
"computegpu": {
"url": "https://mcp.computegpu.com/mcp"
}
}
}
[mcp_servers.computegpu]
url = "https://mcp.computegpu.com/mcp"
{
"mcpServers": {
"computegpu": {
"url": "https://mcp.computegpu.com/mcp"
}
}
}
{
"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.
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
computegpu_get_started
computegpu_signup
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| 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 |
Deploy apps, databases and previews to your own servers. Run Ployz Cloud from your agent.
Deploy from your terminal, and give an AI coding agent the same abilities over MCP.
Deploy a built website from your coding agent and share one client review link.
Build, backtest, and deploy quantitative trading strategies from your AI agent.
Deploy localhost to a private, authenticated link from your AI coding agent.
Deploy and manage websites and apps on Swiss hosting, with HTTPS, from your AI agent.
Agent-to-agent cloud service: deploys and runs your apps and services — domains, logs, real status.
Deploy any Git branch to a live HTTPS preview URL from your agent. No Dockerfile required.
Answers built from our own checks of this server.