Runcrate is answering right now. Last checked 10 min ago. Last commit 3 Nov 2026.
AI cloud for agents: launch GPUs, run jobs that stop their own billing, schedule runs.
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 22 October 2026. No other catalogue keeps this.
Today is the operative word: we check Runcrate every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.
claude mcp add runcrate --transport http https://mcp.runcrate.ai/mcp
https://mcp.runcrate.ai/mcp
[mcp_servers.runcrate]
url = "https://mcp.runcrate.ai/mcp"
{
"mcpServers": {
"runcrate": {
"url": "https://mcp.runcrate.ai/mcp"
}
}
}
{
"servers": {
"runcrate": {
"type": "http",
"url": "https://mcp.runcrate.ai/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.runcrate.ai/mcp | streamable-http | sign-in | 135 ms | 10 min ago |
Schedule wake-ups for AI agents that bring back their saved state and thread when they fire.
Rent cloud GPUs from AI agents: live prices, VRAM estimates, launch, logs and stop.
On-demand GPU nodes for agents: create nodes, run commands, and submit jobs, billed by the minute.
async/await for LLM agents: spawn and await sub-agents scheduled on your own GPUs
Rent cloud GPUs from your agent: live catalogue, deploy, stop, destroy. Per-second billing.
Catch AI agent loops: halt runs that repeat the same failing step or tool call.
Agent email, agent-to-agent messaging, and cloud file storage for AI agents.
Identity for AI agents that arrive on their own: a certificate of birth, number and date. Free.
Answers built from our own checks of this server.