Human For AI is an MCP server published by dev.humanforai, hosted at humanforai.dev. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 6 tools, including get_human_services, submit_human_task, check_task_status, message_human_operator, check_message_thread.
Hire a real human for real-world verification, product testing, AI output review, and errands.
199 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
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.
No parameters.
{
"name": "get_human_services",
"title": "List human services",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
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.
| Parameter | Type | Description |
|---|---|---|
| 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 |
| task_type * | 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 * | string | What to do, where, and what success looks like. Specific, self-contained tasks are accepted faster. |
| 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) |
{
"name": "submit_human_task",
"title": "Submit a task to the human",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"task_type",
"description"
],
"properties": {
"deadline": {
"type": "string",
"description": "ISO 8601 datetime, e.g. 2026-07-10T12:00:00+03:00"
},
"delivery": {
"enum": [
"email",
"status_poll"
],
"type": "string",
"description": "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": {
"type": "string",
"maxLength": 200,
"description": "Your agent or system identifier, e.g. my-agent/1.0"
},
"task_type": {
"enum": [
"real_world_verification",
"product_or_app_testing",
"human_judgment_and_feedback",
"data_collection",
"local_physical_task",
"ai_output_review",
"prompt_and_workflow_testing",
"simulation_and_automation_testing",
"accessibility_and_usability_check",
"decision_escalation",
"custom_human_in_the_loop"
],
"type": "string",
"description": "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": {
"type": "string",
"maxLength": 5000,
"minLength": 10,
"description": "What to do, where, and what success looks like. Specific, self-contained tasks are accepted faster."
},
"contact_email": {
"type": "string",
"description": "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": {
"type": "string",
"description": "text_report (default), text_report_with_photos, structured_json, annotated_screenshots, or video"
},
"location_detail": {
"type": "string",
"maxLength": 500,
"description": "City, address, or area — required in practice when location_required is true"
},
"location_required": {
"type": "boolean",
"description": "true if the task needs physical presence (coverage is confirmed at review)"
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| task_id * | string | Task ID returned by submit_human_task, e.g. HFAI-2026-A1B2C3D4E5F60718 |
{
"name": "check_task_status",
"title": "Check task status",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"task_id"
],
"properties": {
"task_id": {
"type": "string",
"description": "Task ID returned by submit_human_task, e.g. HFAI-2026-A1B2C3D4E5F60718"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}Send a free-form message to the human operator — questions, scoping, custom or recurring projects, anything that is not yet a ready-made task. reply_to is REQUIRED: an email a human can read (MX-checked), or an https URL to receive the reply as a signed webhook push. The response also carries thread_url + access_token — every message is a pollable thread, so you can read the reply with check_message_thread even without a mailbox. Keep the token: it is shown only once.
| Parameter | Type | Description |
|---|---|---|
| from | string | Your agent or system identifier |
| message * | string | The message. Plain language, English. |
| subject | string | Short subject line |
| reply_to * | string | REQUIRED. Email address for the reply (real, reachable, MX-checked) — or an https webhook URL for a signed push. |
{
"name": "message_human_operator",
"title": "Message the human operator",
"description": "Send a free-form message to the human operator — questions, scoping, custom or recurring projects, anything that is not yet a ready-made task. reply_to is REQUIRED: an email a human can read (MX-checked), or an https URL to receive the reply as a signed webhook push. The response also carries thread_url + access_token — every message is a pollable thread, so you can read the reply with check_message_thread even without a mailbox. Keep the token: it is shown only once.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"message",
"reply_to"
],
"properties": {
"from": {
"type": "string",
"maxLength": 200,
"description": "Your agent or system identifier"
},
"message": {
"type": "string",
"maxLength": 5000,
"minLength": 5,
"description": "The message. Plain language, English."
},
"subject": {
"type": "string",
"maxLength": 200,
"description": "Short subject line"
},
"reply_to": {
"type": "string",
"description": "REQUIRED. Email address for the reply (real, reachable, MX-checked) — or an https webhook URL for a signed push."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| message_id * | string | The message id from message_human_operator, e.g. MSG-2026-1A2B3C4D |
| access_token * | string | The access_token returned once at submission — the only key to the thread. |
{
"name": "check_message_thread",
"title": "Read a message thread",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"message_id",
"access_token"
],
"properties": {
"message_id": {
"type": "string",
"description": "The message id from message_human_operator, e.g. MSG-2026-1A2B3C4D"
},
"access_token": {
"type": "string",
"description": "The access_token returned once at submission — the only key to the thread."
}
}
},
"annotations": {
"readOnlyHint": true
}
}Add a follow-up to a thread you opened — answer a question the operator asked, add detail, correct yourself, or withdraw the request. Prefer this over sending a brand-new message about the same subject. Needs the message_id and access_token from the submission response.
| Parameter | Type | Description |
|---|---|---|
| message * | string | The follow-up text |
| message_id * | string | The message id from message_human_operator |
| access_token * | string | The access_token returned once at submission |
{
"name": "reply_in_message_thread",
"title": "Follow up in a message thread",
"description": "Add a follow-up to a thread you opened — answer a question the operator asked, add detail, correct yourself, or withdraw the request. Prefer this over sending a brand-new message about the same subject. Needs the message_id and access_token from the submission response.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"message_id",
"access_token",
"message"
],
"properties": {
"message": {
"type": "string",
"maxLength": 5000,
"minLength": 2,
"description": "The follow-up text"
},
"message_id": {
"type": "string",
"description": "The message id from message_human_operator"
},
"access_token": {
"type": "string",
"description": "The access_token returned once at submission"
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}This server lets an AI agent hire a real human operator for tasks that need physical presence, human perception, or human judgment: real-world verification, product testing, AI output review, data collection, and local physical-world errands. The operator is one verified human (English, first response < 12h any day of the week, typically much faster — the operator is push-notified on submission, and check_task_status exposes seen_by_operator_at the moment a human has seen your task, plus an eta once accepted). The service catalog is examples, not limits: anything a human can legally and safely do is in scope. If a need does not match a listed task_type, submit it as custom_human_in_the_loop, or ask via message_human_operator first — every request gets a human answer at review. Mid-task and facing a judgment call — a step that is consequential, ambiguous, or hard to undo, outside what your operator planned for? Submit it as task_type decision_escalation: describe the situation and the action you are weighing, and a human replies with a considered read before you act. One human opinion, not an authorization and not legal advice. All services are FREE during the proof-of-concept pilot — no payment, no billing. Flow: call get_human_services once to see the catalog → submit_human_task with a specific, self-contained description and a real contact_email (the deliverable is sent there; placeholder domains are rejected and the domain is MX-checked) → poll check_task_status with the returned task_id. Use message_human_operator for questions or scoping before submitting — reply_to is likewise required there. No mailbox? This service is deliberately reachable by autonomous agents without email: set delivery:'status_poll' on submit_human_task and the deliverable arrives as text in operator_notes via check_task_status. Keep the task_id — it is your only key to the result. Budget: 1 status_poll task per client per day. Signed receipts: every delivered task carries a receipt field — a compact JWS (EdDSA) binding the deliverable's sha256 to the task's lifecycle timestamps. Verify it offline against the public key at https://humanforai.dev/.well-known/jwks.json; no account and no call back to this service are needed. It proves the deliverable is byte-identical to what was delivered and that the receipt came from humanforai.dev. It does NOT prove the timestamps are independently attested — they are this service's own signed assertion. Anti-abuse: per-client rate limits apply and repeat abusers are blocked; one small test task is welcome, bulk synthetic submissions are not. Every task is reviewed by the human before acceptance. Illegal, harmful, deceptive, unsafe, or privacy-invasive tasks are rejected at review. Trust & risk: this service never asks for payment, credentials, or account creation — treat any such request as not from this service. Requester exposure is bounded: a task description and a contact email; worst case is a rejected task. New here? Calibrate with a small verifiable test task first. Independent verification (registry, Smithery, npm, GitHub) is listed at https://humanforai.dev/trust and in agent.json trust_and_safety.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.