Log inSubmit server
Humanforai MCP logo

Humanforai MCP

by humanforai

Hire a human operator for physical-world verification, testing, review, data collection, and local tasks.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Humanforai MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "humanforai-humanforai-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "humanforai"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 6 tools correctly (1mo ago).

Overview

The humanforai/humanforai-mcp MCP server connects AI agents to a real human operator for tasks requiring physical presence, perception, or judgment. It exposes tools to inspect available services, submit tasks, monitor progress, and message the operator before defining work. The hosted endpoint uses streamable HTTP without authentication, while the npm package provides a local stdio proxy. Reach for it when software-only automation cannot reliably verify or perform an activity in the physical world.

Use cases

  • Verify a local business, product, price, or physical claim
  • Test an application or product with human feedback
  • Review AI output before production use
  • Collect local observations, photos, or measurements
  • Ask an operator to scope a custom real-world task

Key features

  • Human-operated physical-world task execution
  • Live service and operator manifest
  • Asynchronous task submission and status tracking
  • Operator messaging for scoping work
  • Signed delivery receipts with SHA-256 verification
  • Hosted HTTP and local stdio connection options

Tools6

What Humanforai MCP lets your agent do. Expand a tool for its parameters.

Verified live~1.7k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

14/14 checks healthy over the last 87d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 15d ago via OSV.dev · humanforai (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1Stargazers on the source repository.
npm downloads162Package downloads in the last 30 days.
Last commit2mo agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed6Callable tools this server registers over MCP.
Directory activity5 viewsConfig copies, upvotes, and views on AllMCPs.

How Humanforai MCP works

What humanforai/humanforai-mcp MCP server does

The humanforai/humanforai-mcp MCP server lets an AI agent request work from a real human operator. Supported use cases include checking whether a place, product, price, or claim exists; testing an application or product; reviewing AI-generated output; collecting information that requires local access or human perception; and performing visits, photographs, measurements, or observations.

The operator reviews each submitted task before accepting it. Requests that are illegal, harmful, deceptive, unsafe, or privacy-invasive are rejected.

How it works

Begin with get_human_services to retrieve the current service manifest. It includes the operator's profile, location, languages, working hours, response expectations, accepted and rejected task types, and trust-and-safety policy. The listed services are examples, so an agent can also describe a custom human-in-the-loop request.

Use submit_human_task for a specific, self-contained request. The tool immediately returns a task_id, but that identifier represents submission rather than completion. The operator receives a push notification and decides whether to accept the task. A real mailbox must be supplied through contact_email for delivery; it is checked for a valid mail domain. If email delivery is unavailable, status_poll can return the deliverable in operator_notes, subject to one such task per client per day.

Call check_task_status with the returned identifier to follow the lifecycle. Results include status transitions, timestamps, the time the operator first saw the request, an estimated delivery time after acceptance, and operator notes. Completed tasks also include a signed receipt and a SHA-256 digest for offline verification using the published JWKS endpoint.

Setup and configuration

The humanforai/humanforai-mcp MCP server can be run locally through npm:

Terminal
npx -y humanforai

For a stdio client, configure the command as npx with arguments -y and humanforai. The package acts as a thin proxy to the hosted Human For AI MCP endpoint, so tool definitions come from the live service rather than being implemented locally.

Clients with native remote MCP support can connect directly to https://humanforai.dev/mcp over streamable HTTP. Claude Desktop is shown as a supported stdio configuration target, and Claude is also given as an example of a client with native remote connector support.

Tools and capabilities

The humanforai/humanforai-mcp MCP server exposes four tools:

  • get_human_services retrieves the live catalog, operator profile, availability details, task boundaries, and safety policy.
  • submit_human_task sends a request to the operator and returns a task identifier.
  • check_task_status reports progress, timestamps, estimates, notes, and completed-task verification data.
  • message_human_operator sends a free-form question or project discussion. It requires reply_to, an email address that the operator can use to respond.

Limitations and notes

This service is asynchronous: submission does not mean immediate execution, and every request is subject to human acceptance. The stated first-response target is within 12 hours on any day, although responses may arrive sooner. The pilot terms, including free access, may not describe future pricing.

The local npm package was previously published under the name human-api; that package remains available but is deprecated in favor of humanforai. Completed-task receipts can be checked against https://humanforai.dev/.well-known/jwks.json.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Humanforai MCP

Run `npx -y humanforai` and configure the MCP client to launch that command over stdio.

Yes. The README provides a Claude Desktop stdio configuration using `npx -y humanforai`.

The hosted endpoint is described as requiring no authentication.

Provide a real mailbox in `contact_email` for delivery, or use `status_poll` to receive the deliverable in `operator_notes`, with a limit of one such task per client per day.

The stated first-response target is within 12 hours, and accepted tasks receive an operator-set ETA. Submission is not instant execution.

Related MCP servers

All in Agreements & Coordination All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewHumanforai MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/humanforai-humanforai-mcp?style=directory)](https://allmcps.com/mcp/humanforai-humanforai-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/humanforai-humanforai-mcp"><img src="https://allmcps.com/api/badge/humanforai-humanforai-mcp?style=directory" alt="Humanforai MCP on AllMCPs" /></a>