1RBT terse agent record is listed as active in the registry but did not answer our last check.
Record agent tasks, get back how many finished without a human. Closed beta, nothing billed.
Over the last week it answered 0.0% 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 13 min ago.
claude mcp add rbt --transport http https://1rbt1.dynv6.net/mcp
{
"mcpServers": {
"rbt": {
"url": "https://1rbt1.dynv6.net/mcp"
}
}
}
[mcp_servers.rbt]
url = "https://1rbt1.dynv6.net/mcp"
{
"mcpServers": {
"rbt": {
"url": "https://1rbt1.dynv6.net/mcp"
}
}
}
{
"mcpServers": {
"rbt": {
"url": "https://1rbt1.dynv6.net/mcp"
}
}
}
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://1rbt1.dynv6.net/mcp | streamable-http | answering | 346 ms | 13 min ago |
Agents browse Wild Wallet bodies + closets and file human-approved merge requests.
Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
Real human judgment as agent tools — ask a question, get a structured human answer back.
Run agent tasks, track progress, retrieve files, and search meeting notes with Runable.
Obfuscate Python before shipping; reverse-map tracebacks with your AI agent. No phone-home.
Hand a human a rich interactive UI by URL and get structured data back, from any MCP client.
Human-in-the-Loop API: AI agents create forms, share URLs with humans, get JSON back.
Human judgment for AI agents: discover capabilities, get quotes, and track paid human tasks.
Answers built from our own checks of this server.