humanforai.dev publishes an Agentic Resource Discovery manifest at /.well-known/ard.json, declaring what an AI agent can call on this domain. Everything below is read from that file. First seen by our crawler on 31 August 2026.
| Declared resource | Type |
|---|---|
| Human For AI — llms.txtanswers in 232ms One-page overview for language models: what the service does, key facts, and links to every machine-readable endpoint. endpoint: https://humanforai.dev/llms.txtidentifier: urn:air:humanforai.dev:docs:llms-txtdocs llms-txt | text/markdown |
| Human For AI — MCP serveranswers in 193msv1.8.0 MCP server (streamable HTTP, no auth) at https://humanforai.dev/mcp where an AI agent hires a verified human operator: real-world verification, product testing, AI output review, data collection, and physical-world tasks. endpoint: https://humanforai.dev/.well-known/mcp/server-card.jsonidentifier: urn:air:humanforai.dev:server:human-for-aipublished to be found for: hire a human to verify a store price in the real world · get a human to test my app and report findings · have a human review this AI-generated output · send a human to check whether this business location exists human-in-the-loop mcp real-world verification real_world_verification product_or_app_testing ai_output_review data_collection trust identity: https://humanforai.dev/.well-known/jwks.json | application/mcp-server-card+json |
| Human For AI — REST APIanswers in 176msv1.9.0 Public REST API (no auth): submit tasks, poll status, message the operator. Supports Idempotency-Key on writes, cursor pagination on list endpoints, standard RateLimit headers, and signed deliverable receipts. endpoint: https://humanforai.dev/openapi.jsonidentifier: urn:air:humanforai.dev:api:rest-v1published to be found for: submit a task to a human over a REST API · poll the status of a human task by id rest openapi human-in-the-loop | application/vnd.oai.openapi+json |
| Human For AI — agent manifestanswers in 215msv1.9.0 Canonical platform self-description: services catalog, endpoints, task schema, accepted and rejected task types, pricing, response expectations, and trust & safety policy. endpoint: https://humanforai.dev/.well-known/agent.jsonidentifier: urn:air:humanforai.dev:manifest:agent-jsonmanifest discovery | application/json |
https://humanforai.dev/.well-known/ard.json, this publisher's own file. Identifiers are reproduced exactly as published.
Of the resources listed, 4 have been probed for reachability.
"Answers" and "no response" describe only whether an endpoint replied when last probed:
services go down and come back, and an entry is demoted rather than removed. None of this
is a trust, quality or safety rating.
https://neuronto.com/search, or connect an agent to https://neuronto.com/mcp.
If this is your domain, the free console shows what a registry
sees when it reads your manifest.