dev.humanforaiPublished by humanforai.devOfficial publisherv0.1.4Updated Oct 24, 2026
Hire a real human for real-world verification, product testing, AI output review, and errands.
Connects an AI assistant to a real human operator for real-world verification, product testing, human judgment, and local errands.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/dev.humanforai%2Fhumanforai/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"human-for-ai": {
"type": "http",
"url": "https://humanforai.dev/mcp"
}
}
}[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:
get_human_services for the full catalogAll 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.
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 acceptedstatus_history — every transition (submitted → accepted → delivered, or rejected) with timestampsYou don't need this package — connect directly to the hosted endpoint (streamable HTTP, no auth):
E.g. Claude (Settings → Connectors → Add custom connector), or:
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.
get_human_services — see what the operator can dosubmit_human_task — be specific and self-contained; include contact_email to receive the deliverablecheck_task_status — poll with the returned task_idMIT
Source: README.md at commit c067642
List 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.
Takes no parameters.
Submit a task to the human
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.
deadlinedeliveryrequestertask_typerequireddescriptionrequiredcontact_emailoutput_formatlocation_detaillocation_requiredCheck 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.
task_idrequiredMessage the 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.
frommessagerequiredsubjectreply_torequiredRead a 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.
message_idrequiredaccess_tokenrequiredFollow up in a 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.
messagerequiredmessage_idrequiredaccess_tokenrequired100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
claude mcp add human-for-ai -- npx -y humanforai{ "mcpServers": { "human-for-ai": { "command": "npx", "args": ["-y", "humanforai"] } }}https://humanforai.dev/mcpclaude mcp add --transport http human-for-ai https://humanforai.dev/mcp