dev.humanforai/humanforai (MCP Server)

This MCP server provides a “Human For AI” human endpoint for AI agents. It is intended to hire a real human operator for tasks requiring physical presence, human perception, or human judgment. The repository is described as supporting real-world verification, product testing, AI output review, and errands.

🛠️ Key Features

Human endpoint for AI agents
Supports hiring a real human operator
Focus on physical presence and human perception/judgment
Tool count: 4

🚀 Use Cases

Real-world verification
Product testing
AI output review
Errands

⚡ Developer Benefits

Integrates human-in-the-loop capability into MCP-based agent workflows
Explicit alignment with MCP and agent tooling (topics: mcp, mcp-server, model-context-protocol, agents, ai-agents, automation)

⚠️ Limitations

Scope is tied to tasks that require a human operator (not fully autonomous tasks)

📦 Related Topics

human-in-the-loop, claude, automation, mcp, mcp-server, model-context-protocol

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, any day of the week — typically much faster: the operator is push-notified the moment a task arrives.

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

Status transparency

check_task_status shows progress in real time, not just the final result:

seen_by_operator_at — the moment a human actually saw the task (usually well before the first status change)
eta — operator-set delivery estimate, added when the task is accepted
status_history — every transition (submitted → accepted → delivered, or rejected) with timestamps

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

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

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

Human For AI

dev.humanforai/humanforai (MCP Server)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

📦 Related Topics

Topics

get_human_services

submit_human_task

check_task_status

message_human_operator