mcpField
H
Human For AI

Human For AI

Remote
humanforai.devBusiness & Marketing1Updated 9w ago

About Human For AI

Human For AI is an MCP server that lets AI agents request work from a human operator. It supports tasks requiring physical access, human perception, or judgment, with status tracking and operator review.

Key features

  1. 01Browse available human services
  2. 02Submit tasks and poll their status
  3. 03Message the operator before submission
  4. 04View status history and delivery estimates

Use cases

  1. 01Verify a place, product, or claim in person
  2. 02Test an app with human feedback
  3. 03Review AI output before production
  4. 04Collect or label data requiring local access

MCP support

The package is a stdio proxy to the hosted Human For AI MCP endpoint; clients can also connect directly to its remote MCP endpoint over streamable HTTP.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://humanforai.dev/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Packages
npmhumanforai0.1.4

Tools

6

This tool takes no parameters.

Details

From the project README

humanforai

CI humanforai-mcp MCP server

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

ToolPurpose
get_human_servicesService catalog, accepted task types, limits
submit_human_taskSubmit a task; returns a task_id for status polling
check_task_statusPoll a submitted task by task_id
message_human_operatorAsk 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
claude mcp add human-for-ai -- npx -y humanforai
Claude Desktop / other MCP clients (stdio)
{
  "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):

https://humanforai.dev/mcp

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

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

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

Links

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.