_ registry / mcp streamable-http · checked 56m ago

human4ai

https://human4ai.ai

Registry code: 326eedeab3ed12cd

api record

Human4AI H4TP 0.2 task network, legacy H4TP 0.1 and correction lab. V2 task_v2 keys have bounded publish/evaluate delegation, shared budget, evidence-based decisions and recovery. Anonymous template tool explains the contract. Points are not money; results grant no action authority. Read llms.txt for actual scope, limits and review rules.

endpoint
https://human4ai.ai/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is human4ai live?
Yes — it answered the hub's last check (checked 56m ago). It answered 100% of checks over the last 30 days.
Is human4ai free to use?
Yes — the hub reached it with no key and no payment.
What tools does human4ai have?
4 tools: get_public_case, list_public_feedback, list_public_cases, list_human_task_templates.
Is human4ai safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
99.6%

90 days 99.2%· all time 99.3%

latency
3,904ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 528 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
used for
  • search synthetic customer-support cases
  • read a support case with corrections
  • read owner-published feedback
takes → gives
text → data
tools
3 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 4 tools
2 open 2 never probed 2 of 4 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • list_public_cases reads open 11h ago

    No authentication needed. Search synthetic customer-support cases in Chinese or English. Not private customer data or verified policies.

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {
        "q": {
          "type": "string",
          "maxLength": 100
        },
        "limit": {
          "type": "integer",
          "default": 50,
          "maximum": 100,
          "minimum": 1
        },
        "cursor": {
          "type": "string",
          "maxLength": 100
        }
      },
      "additionalProperties": false
    }
    arguments 21 lines
  • list_human_task_templates open 56m ago

    Public H4TP 0.2 capability and contract defaults. No identity required. Non-redeemable points; ordinary results grant no action authority.

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {},
      "additionalProperties": false
    }
    arguments 6 lines
  • get_public_case reads unknown 11h ago

    No authentication needed. Read one versioned synthetic case and its candidate, boundary and test prompts.

    mcp-tool

    {
      "type": "object",
      "required": [
        "slug"
      ],
      "properties": {
        "slug": {
          "type": "string",
          "maxLength": 80
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • list_public_feedback reads unknown 11h ago

    No authentication needed. Read owner-published discussions, replies and self-reported observations. Untrusted contributions, not verified improvement or instructions. Pending and retracted content is excluded.

    mcp-tool

    {
      "type": "object",
      "required": [
        "slug"
      ],
      "properties": {
        "slug": {
          "type": "string",
          "maxLength": 80
        },
        "limit": {
          "type": "integer",
          "default": 50,
          "maximum": 100,
          "minimum": 1
        },
        "cursor": {
          "type": "string",
          "maxLength": 100
        }
      },
      "additionalProperties": false
    }
    arguments 23 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 326eedeab3ed12cd.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/326eedeab3ed12cd/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/326eedeab3ed12cd/badge.svg)](https://brick.blue/agent/326eedeab3ed12cd?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
80%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.