Human For AI

Official4 toolsLive

by humanforai · JavaScript

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

Topics

agentsai-agentsautomationclaudehuman-in-the-loopmcpmcp-servermodel-context-protocol

Captured live from the server via tools/list.

get_human_services

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.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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). Free during the pilot. Include contact_email — it is how the deliverable reaches you.

Parameters8

task_type	string	required	Service category — see get_human_services for descriptions
description	string	required	What to do, where, and what success looks like. Specific, self-contained tasks are accepted faster.
location_required	boolean	optional	true if the task needs physical presence (coverage is confirmed at review)
location_detail	string	optional	City, address, or area — required in practice when location_required is true
deadline	string	optional	ISO 8601 datetime, e.g. 2026-07-10T12:00:00+03:00
output_format	string	optional	text_report (default), text_report_with_photos, structured_json, annotated_screenshots, or video
contact_email	string	optional	Where the deliverable and clarifying questions are sent. Strongly recommended.
requester	string	optional	Your agent or system identifier, e.g. my-agent/1.0

Raw schema

{
  "type": "object",
  "properties": {
    "task_type": {
      "type": "string",
      "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",
        "custom_human_in_the_loop"
      ],
      "description": "Service category — see get_human_services for descriptions"
    },
    "description": {
      "type": "string",
      "minLength": 10,
      "maxLength": 5000,
      "description": "What to do, where, and what success looks like. Specific, self-contained tasks are accepted faster."
    },
    "location_required": {
      "description": "true if the task needs physical presence (coverage is confirmed at review)",
      "type": "boolean"
    },
    "location_detail": {
      "description": "City, address, or area — required in practice when location_required is true",
      "type": "string",
      "maxLength": 500
    },
    "deadline": {
      "description": "ISO 8601 datetime, e.g. 2026-07-10T12:00:00+03:00",
      "type": "string"
    },
    "output_format": {
      "description": "text_report (default), text_report_with_photos, structured_json, annotated_screenshots, or video",
      "type": "string"
    },
    "contact_email": {
      "description": "Where the deliverable and clarifying questions are sent. Strongly recommended.",
      "type": "string"
    },
    "requester": {
      "description": "Your agent or system identifier, e.g. my-agent/1.0",
      "type": "string",
      "maxLength": 200
    }
  },
  "required": [
    "task_type",
    "description"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

check_task_status

Look up a submitted task by its task_id. Returns current status (submitted → under_review → accepted → in_progress → delivered, or rejected), status history with timestamps, and any operator notes.

Parameters1

task_id

string

required

Task ID returned by submit_human_task, e.g. HFAI-2026-A1B2C3D4

Raw schema

{
  "type": "object",
  "properties": {
    "task_id": {
      "type": "string",
      "description": "Task ID returned by submit_human_task, e.g. HFAI-2026-A1B2C3D4"
    }
  },
  "required": [
    "task_id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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. Include reply_to (an email you or your principal can read); it is the only way the operator can answer.

Parameters4

message	string	required	The message. Plain language, English.
reply_to	string	optional	Email address for the reply — strongly recommended
subject	string	optional	Short subject line
from	string	optional	Your agent or system identifier

Raw schema

{
  "type": "object",
  "properties": {
    "message": {
      "type": "string",
      "minLength": 5,
      "maxLength": 5000,
      "description": "The message. Plain language, English."
    },
    "reply_to": {
      "description": "Email address for the reply — strongly recommended",
      "type": "string"
    },
    "subject": {
      "description": "Short subject line",
      "type": "string",
      "maxLength": 200
    },
    "from": {
      "description": "Your agent or system identifier",
      "type": "string",
      "maxLength": 200
    }
  },
  "required": [
    "message"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

README.md3 KBView on GitHub

humanforai

MCP server for Human For AI — a human endpoint for AI agents. Let your AI agent hire a real human operator for tasks that need physical presence, human perception, or human judgment:

Real-world verification — confirm a place, product, price, or claim exists, with photo/text evidence
Product or app testing — a real human installs, uses, and reports
Human judgment and feedback — tone, clarity, trustworthiness, design quality
AI output review — human review before your output reaches production
Data collection — gathering/labeling that needs human perception or local access
Local physical-world tasks — visit, photograph, check, measure, observe
…and more — call get_human_services for the full catalog

All services are free during the proof-of-concept pilot. No API key, no payment. Every task is reviewed by the human operator before acceptance; illegal, harmful, deceptive, unsafe, or privacy-invasive tasks are rejected. First response within 12 hours on working days (Sun–Thu).

Tools

Tool	Purpose
`get_human_services`	Service catalog, accepted task types, limits
`submit_human_task`	Submit a task; returns a `task_id` for status polling
`check_task_status`	Poll a submitted task by `task_id`
`message_human_operator`	Ask questions / scope work before submitting

Setup

Claude Code

bash

claude mcp add human-for-ai -- npx -y humanforai

Claude Desktop / other MCP clients (stdio)

json

{
  "mcpServers": {
    "human-for-ai": {
      "command": "npx",
      "args": ["-y", "humanforai"]
    }
  }
}

Clients with native remote MCP support

You don't need this package — connect directly to the hosted endpoint (streamable HTTP, no auth):

code

https://humanforai.dev/mcp

E.g. Claude (Settings → Connectors → Add custom connector), or:

bash

claude mcp add --transport http human-for-ai https://humanforai.dev/mcp

How it works

This package is a thin stdio proxy to the hosted Human For AI MCP endpoint. Tool definitions come from the live server, so they are always current — the package itself has no logic to go stale.

Previously published as human-api, which still works but is deprecated in favor of this package.

Typical flow

get_human_services — see what the operator can do
submit_human_task — be specific and self-contained; include contact_email to receive the deliverable
check_task_status — poll with the returned task_id

License

MIT

Install

Tools (4)

get_human_servicessubmit_human_taskcheck_task_statusmessage_human_operator

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "humanforai": {
      "command": "npx",
      "args": [
        "-y",
        "humanforai@0.1.4"
      ]
    }
  }
}

Topics

get_human_services

submit_human_task

check_task_status

message_human_operator

humanforai

Tools

Setup

Claude Code

Claude Desktop / other MCP clients (stdio)

Clients with native remote MCP support

How it works

Typical flow

Links

License

Install