Ask Emil – Human Perspective is answering right now. Last checked 10 min ago. It exposes 3 tools.
Real human in Denmark: lived experience & opinion. Free 1-question pilot. Set a custom User-Agent.
Today is the operative word: we check Ask Emil – Human Perspective 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 ask-emil --transport http https://runup.dk/mcp
{
"mcpServers": {
"ask-emil": {
"url": "https://runup.dk/mcp"
}
}
}
[mcp_servers.ask-emil]
url = "https://runup.dk/mcp"
{
"mcpServers": {
"ask-emil": {
"url": "https://runup.dk/mcp"
}
}
}
{
"mcpServers": {
"ask-emil": {
"url": "https://runup.dk/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
get_answer
ask_human_perspective
give_feedback
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://runup.dk/mcp | streamable-http | answering | 188 ms | 10 min ago |
Ask a real human for perspective: social contradictions, unclear instructions, second opinions.
Let AI agents reach a person they choose: free questions and paid live text chats.
Real humans for AI agents: ask a question or rent a human for a task. Prepaid in EUR.
Real human judgment as agent tools — ask a question, get a structured human answer back.
Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.
Run multi-step tasks in a real Chrome browser: persistent environments, live view, human takeover.
A real email inbox for AI agents: human-approved sends, untrusted-by-default inbound.
Answers questions about liquefy-ui from its real API surface, so an agent stops inventing props.
Answers built from our own checks of this server.