# Human For AI

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

- name: dev.humanforai/humanforai
- version: 0.1.4
- connection class: R0 (autonomous)
- trust: 93/100
- quality: 84/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/dev.humanforai%2Fhumanforai
- tools: https://api.protogrid.dev/v1/servers/dev.humanforai%2Fhumanforai/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "humanforai": {
      "type": "http",
      "url": "https://humanforai.dev/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 65
- provenance: 100
- drivers: +repository +namespace-matches-repo +dns-namespace +website +reachable +uptime-99% ~updated-98d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 84/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 93 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 6 of 6 tools declare readOnlyHint or destructiveHint
- warn `tools.directory_hints`: 3 of 6 tools declare all four hints; missing: get_human_services (destructiveHint, idempotentHint); check_task_status (destructiveHint, idempotentHint); check_message_thread (destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 1,764 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: 67 (weight 15)

- pass `deps.known_vulns`: no known advisory in 98 resolved packages
- fail `deps.mcp_sdk_version`: @modelcontextprotocol/sdk 1.30.1 has 1 known advisory (GHSA-6qxp-vccf-f47h); update @modelcontextprotocol/sdk to 1.31.0 or later
- pass `deps.resolvable`: humanforai@0.1.4 resolved: 98 packages

- tools: 6, about 1,764 tokens to load them all
- tool set hash: ec2cd6f684a4e77a617ab06386df83e1
- badge: [![protogrid quality](https://protogrid.dev/badge/dev.humanforai/humanforai.svg)](https://protogrid.dev/servers/dev.humanforai/humanforai)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Dependencies

- npm humanforai@0.1.4: resolved, 97 dependencies, MCP SDK @modelcontextprotocol/sdk 1.30.1
  - GHSA-6qxp-vccf-f47h (high) in `` @modelcontextprotocol/sdk@1.30.1 ``, direct, fixed in `` 1.31.0 ``, advisory summary: "MCP TypeScript SDK: OAuth client could send credentials to an authorization server chosen by the MCP server" https://osv.dev/vulnerability/GHSA-6qxp-vccf-f47h

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://humanforai.dev/mcp (streamable-http, auth none, reachable true, uptime30d 0.9915254)

## Packages

- npm humanforai@0.1.4

## Tools (6)

- `check_message_thread`: 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.
- `check_task_status`: 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.
- `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. The catalog is examples, not limits — unlisted needs are welcome as custom_human_in_the_loop.
- `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. 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.
- `reply_in_message_thread`: 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.
- `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). 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.