Human For AI

Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.

Hire a real human for real-world verification, product testing, AI output review, and errands.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Human For AI": {
      "url": "https://humanforai.dev/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (6)

• get_human_services read-only

  Fetch the Human For AI manifest: available services, operator profile (location, languages, working hours), response times, accepted and rejected task types, and trust & safety policy. Call this first to decide whether and how to hire the human. The catalog is examples, not limits — unlisted needs are welcome as custom_human_in_the_loop.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• submit_human_task

  Submit a task for the human operator to perform in the real world. Returns a task_id immediately; the human reviews every task before accepting it (this is not instant execution). The operator is push-notified on submission; check_task_status shows seen_by_operator_at once a human has seen the task. Free during the pilot. contact_email must be a real mailbox (MX-checked) — it is how the deliverable reaches you. No mailbox? Set delivery to 'status_poll' instead: the deliverable arrives as text in operator_notes via check_task_status (limited to 1 such task per client per day). In hosts that support MCP Apps the result also renders as a task status card with a Refresh button; the JSON result carries the same data.

  Parameters:

  • task_type (required) — string — Service category — see get_human_services for descriptions. The list is not exhaustive: use custom_human_in_the_loop for anything that fits no other category
  • description (required) — string — What to do, where, and what success looks like. Specific, self-contained tasks are accepted faster.
  • deadline — string — ISO 8601 datetime, e.g. 2026-07-10T12:00:00+03:00
  • delivery — string — How the deliverable reaches you. 'email' (default) needs contact_email. 'status_poll' is the no-mailbox path for autonomous agents: the result arrives as text in operator_notes via check_task_status — keep the task_id, it is your only key. Budget: 1 status_poll task per client per day.
  • requester — string — Your agent or system identifier, e.g. my-agent/1.0
  • contact_email — string — Where the deliverable and clarifying questions are sent. Required unless delivery is 'status_poll'. Must be a real, reachable mailbox — placeholder domains are rejected and the domain is MX-checked.
  • output_format — string — text_report (default), text_report_with_photos, structured_json, annotated_screenshots, or video
  • location_detail — string — City, address, or area — required in practice when location_required is true
  • location_required — boolean — true if the task needs physical presence (coverage is confirmed at review)

  Hints: read-only no · destructive no · idempotent no · open-world yes

• check_task_status read-only

  Look up a submitted task by its task_id. Returns current status (submitted → accepted → delivered, or rejected), status history with timestamps, seen_by_operator_at (the moment a human actually saw the task — usually well before the first status change), eta (operator-set delivery estimate, once accepted), and any operator notes. Once delivered, the response also carries receipt (a signed JWS binding the deliverable's sha256 to the lifecycle timestamps) and deliverable_sha256 — verify offline against https://humanforai.dev/.well-known/jwks.json. In hosts that support MCP Apps the result also renders as a task status card (timeline, seen-by-human moment, ETA, operator notes, receipt) with a Refresh button; the JSON result carries the same data.

  Parameters:

  • task_id (required) — string — Task ID returned by submit_human_task, e.g. HFAI-2026-A1B2C3D4E5F60718

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• message_human_operator

  Send a free-form message to the human operator — questions, scoping, custom or recurring projects, anything that is not yet a ready-made task. reply_to is REQUIRED: an email a human can read (MX-checked), or an https URL to receive the reply as a signed webhook push. The response also carries thread_url + access_token — every message is a pollable thread, so you can read the reply with check_message_thread even without a mailbox. Keep the token: it is shown only once.

  Parameters:

  • message (required) — string — The message. Plain language, English.
  • reply_to (required) — string — REQUIRED. Email address for the reply (real, reachable, MX-checked) — or an https webhook URL for a signed push.
  • from — string — Your agent or system identifier
  • subject — string — Short subject line

  Hints: read-only no · destructive no · idempotent no · open-world yes

• check_message_thread read-only

  Read the thread for a message you sent: the original text, every reply oldest-first, and whether the operator has answered. Needs the message_id and the access_token from the submission response. An empty replies list means no answer yet — the operator works at human speed, so poll occasionally rather than in a loop.

  Parameters:

  • message_id (required) — string — The message id from message_human_operator, e.g. MSG-2026-1A2B3C4D
  • access_token (required) — string — The access_token returned once at submission — the only key to the thread.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• reply_in_message_thread

  Add a follow-up to a thread you opened — answer a question the operator asked, add detail, correct yourself, or withdraw the request. Prefer this over sending a brand-new message about the same subject. Needs the message_id and access_token from the submission response.

  Parameters:

  • message_id (required) — string — The message id from message_human_operator
  • access_token (required) — string — The access_token returned once at submission
  • message (required) — string — The follow-up text

  Hints: read-only no · destructive no · idempotent no · open-world yes

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.