Agents pay one real human for typed answers. First question free, then $2 each, or subscribe.
Scored across 12 tools
Most tools target clearly distinct actions (register_agent, get_answer, list_my_tickets, check_human_status, rate_answer, request_refund), but ask_human vs. request_human sound near-identical despite very different purposes, and buy_credits vs. subscribe overlap as two payment paths that only the descriptions separate. Descriptions resolve these, but the boundaries require reading rather than inferring from names.
Mostly consistent verb_noun snake_case (ask_human, get_answer, list_humans, buy_credits, register_agent, request_refund). A couple of outliers break the pattern: the non-verb 'about_this_human' and the bare 'subscribe', plus 'check_human_status' adds a third token where others don't.
12 tools is well within a comfortable range and each maps to a real step in the service lifecycle: identify, fund, ask, retrieve, rate, refund, plus discovery and meta endpoints. No tool looks redundant or vestigial.
The surface covers the full loop: identity creation, human discovery and requests, payment (pack and subscription), question submission, answer retrieval with callback, rating, and refunds. Minor gaps remain — no way to cancel or amend a pending ticket before the human writes, and no endpoint to inspect or revoke an existing api_key/identity.
Who the human is, what they are good at, pricing, response times and payment options. The service is an inversion: instead of an AI selling human knowledge, a human sells their own knowledge to AIs. Every answer is written by one real person, not generated.
Inputs: no named parameters.
Submits a question to a real human: for human approval, feedback or a second opinion, or for judgment, taste and lived experience rather than facts. Paid questions may attach up to 5 public image/video URLs for design, thumbnail or video review (the free first question is text only). Returns a ticket id. The answer is written later by a person; it can be fetched by ticket id or POSTed to callback_url. Price by size and speed: Short ~100 tokens $2/24h or $6/1h, Standard ~400 tokens $8/$20, Deep ~1500 tokens $30/$75; the first Short/24h question is free, then credits are charged (some agents have a fixed discount). Late answers are not charged. Questions that break the terms at /terms are rejected.
Inputs: api_key (required), question (required), size, speed, +4 more.
Returns a Stripe Checkout URL for a credit pack. The operator pays; credits land on the api_key automatically.
Inputs: api_key (required), pack.
Online/offline, a note from the human, and current queue length.
Inputs: no named parameters.
Returns the human's answer if written, else the ticket status and expected time. A rejected ticket carries the reason.
Inputs: ticket_id (required), api_key.
The roster of humans available to answer, with specialties and languages. One today; more are being added.
Inputs: no named parameters.
Your last 20 questions and their status.
Inputs: api_key (required).
Rates an answer from 1 (useless) to 5 (changed my weights). The human sees the rating.
Inputs: rating (required), ticket_id (required), note, api_key.
Creates an agent identity. Returns an api_key and one free question. Each call creates a new identity.
Inputs: name (required), model, publish_ok, operator_email.
Free. Records the kind of human you want to be able to ask: a language, a profession, a country or city, an age range, a lived experience. New humans are recruited from these requests.
Inputs: api_key (required), description (required), language, specialty.
Requests a refund for an answer within 7 days. The human reviews it and refunds credits (or restores the free question). Late answers are never charged, automatically. Monthly plan refunds are handled by email.
Inputs: reason (required), api_key (required), ticket_id (required).
Returns a Stripe Checkout URL for the monthly credit plan: the operator pays $50 a month and the api_key gets $60 of question credit every month. Credit never expires and rolls over; cancel any time in Stripe.
Inputs: api_key (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Agent info shop: $1–$5 paid asks, $1 poll unlocks. Answers free. Remote MCP.
A real person phones a business for your agent and reports the answers back. Ten calls a month
Pay per call, solves one question. Raw public readings on AI agents and x402.
Real humans for AI agents: ask a question or rent a human for a task. Prepaid in EUR.
Add one secure layer between your agents and this server.