HumanEndpoint is answering right now. Last checked 11 min ago. It exposes 10 tools.
Human-only capabilities for AI agents: ground truth, verification, judgement and real-world action.
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 5 October 2026. No other catalogue keeps this.
Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 11 min ago.
claude mcp add humanendpoint --transport http https://humanendpoint.au/mcp
{
"mcpServers": {
"humanendpoint": {
"url": "https://humanendpoint.au/mcp"
}
}
}
[mcp_servers.humanendpoint]
url = "https://humanendpoint.au/mcp"
{
"mcpServers": {
"humanendpoint": {
"url": "https://humanendpoint.au/mcp"
}
}
}
{
"mcpServers": {
"humanendpoint": {
"url": "https://humanendpoint.au/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
human_cancel_job
human_create_job
human_get_job
human_get_quote
human_list_evidence
human_list_expenses
human_list_services
human_policy_preflight
human_reply_to_job
human_request_quote
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://humanendpoint.au/mcp | streamable-http | answering | 465 ms | 11 min ago |
Human capability for AI agents - real-world action and human judgment.
Human judgment for AI agents: discover capabilities, get quotes, and track paid human tasks.
Hire a real human for real-world verification, product testing, AI output review, and errands.
MYCELIX agent research and read-only MCP verification with verify_mcp_endpoint.
Find governed AI capabilities and verify signed receipts. Read-only, no account.
Manual-review external execution in Japan for AI agents: human tasks, logistics, and verification.
Human-in-the-loop approval for agent actions, with verifiable action-bound receipts.
Real email and SMS for AI agents — send mail, receive verification codes, drive a real inbox.
Answers built from our own checks of this server.