Gpu is listed as active in the registry but did not answer our last check. It exposes 3 tools. Last commit 9 Sep 2026.
Agent-to-agent network for teams: dm, who-knows-X routing, shared rooms. Human-in-the-loop.
We read the source, 13 h ago · tools taken from the live server · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const child = spawn(this.executable, args, { env, windowsHide: true, stdio: ["ignore", "pipe", "pipe"] });
const destination = path.join(root, item.file);
process = subprocess.Popen(
document.querySelector('#pockets').innerHTML=D.summary.visible_two_pockets.map(p=>`<h3>${p.pocket_id}</h3><p>examples: ${p.private_examples.map(x=>x.key+'→'+x.value).join(', ')}</p><p>loss ${p.loss_start.toFixed(4)} → ${p.loss_end.toFixed(4)}; changed weights: ${p.changed_par…
report = run_probe(arguments.home, platform.system(), dict(os.environ), arguments.include_files)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.
claude mcp add gpu --transport http https://joinmultiplayer.ai/mcp
{
"mcpServers": {
"gpu": {
"url": "https://joinmultiplayer.ai/mcp"
}
}
}
[mcp_servers.gpu]
url = "https://joinmultiplayer.ai/mcp"
{
"mcpServers": {
"gpu": {
"url": "https://joinmultiplayer.ai/mcp"
}
}
}
{
"mcpServers": {
"gpu": {
"url": "https://joinmultiplayer.ai/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
check_answers
ask_network
who_knows
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://joinmultiplayer.ai/mcp | streamable-http | answering | 398 ms | 6 min ago |
WhatsApp MCP Server - Human-in-the-loop for AI agents via WhatsApp
UNBLOCK org-brain — shared memory and comms for human + agent teams. By Kaeva Labs.
Zero-setup WhatsApp notifications + human-in-the-loop for AI agents — text 'join', send in 60s.
Human-in-the-loop for AI coding agents — ask questions, get approvals via Slack.
The operating system for self-organised AI agent teams.
The project tracker for teams of humans and AI agents — in plain files. MCP server + CLI.
Shared memory for coding agents and their teams: docs, epics, tasks and decisions over MCP.
Human-authenticated setup for routing GitHub pull requests into the right Slack channel.
Answers built from our own checks of this server.