_ registry / mcp streamable-http · checked 1h ago

renthuman

https://renthuman.ru

Registry code: 95322a26fa19655b

api record

RentHuman lets AI agents hire real humans in Russia for physical-world tasks (storefront photos, address checks, offline errands). Payment in USDT. Flow: create_task → poll get_task for applications → accept_application → wait for submitted result → review_result(approve). Write tasks in Russian. Get an API key at https://renthuman.ru/become-customer.html

endpoint
https://renthuman.ru/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 renthuman live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is renthuman free to use?
Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
What tools does renthuman have?
9 tools: create_task, list_tasks, accept_application, review_result, get_balance, get_task, set_webhook, reject_application, ….
Is renthuman 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 99.7%· all time 99.7%

latency
1,060ms

last good check

priced tools
0

of 9 tools

_ answered our checks, 90 days 355 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • unknown → live
_ what it is for
topic
payments & commerce marketplaces & listings
used for
  • hire a person in russia for a physical task
  • review applications from task executors
  • approve a result and pay the executor
  • cancel a task and refund escrow
takes → gives
text, data → data, payments
tools
3 reads4 changes data2 moves money
_ 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 9 tools
9 auth-required 9 of 9 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.

  • create_task moves money auth-required never probed

    Create a task for human executors. Cost = reward × max_executors × 1.2 (20% platform fee), charged from your balance into escrow. Write title and description IN RUSSIAN, clearly, with acceptance criteria — executors are real people in Russia. Returns task_id.

    mcp-tool

    {
  "type": "object",
  "required": [
    "title",
    "description",
    "reward"
  ],
  "properties": {
    "city": {
      "type": "string",
      "description": "City in Russia (e.g. \"Москва\"). Omit for online/any-city tasks"
    },
    "title": {
      "type": "string",
      "description": "Short task title in Russian"
    },
    "reward": {
      "type": "number",
      "description": "Reward per executor in USDT, minimum 1"
    },
    "category": {
      "enum": [
        "photo",
        "delivery",
        "research",
        "testing",
        "other"
      ],
      "type": "string",
      "description": "Task category"
    },
    "deadline": {
      "type": "string",
      "description": "Deadline as ISO 8601 datetime, optional"
    },
    "description": {
      "type": "string",
      "description": "Detailed instructions and acceptance criteria in Russian"
    },
    "max_executors": {
      "type": "integer",
      "description": "How many humans needed, 1-100. Default 1"
    }
  }
}
    arguments 45 lines
  • list_tasks reads auth-required 14h ago

    List all your tasks with statuses: open (accepting applications), in_progress (slots filled), paused, completed, cancelled.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {}
}
    arguments 5 lines
  • accept_application changes data auth-required never probed

    Choose a human executor from pending applications. They will start working on the task.

    mcp-tool

    {
  "type": "object",
  "required": [
    "application_id"
  ],
  "properties": {
    "application_id": {
      "type": "string",
      "description": "Application UUID"
    }
  }
}
    arguments 12 lines
  • review_result moves money auth-required never probed

    Review a submitted result. action=approve pays the executor instantly (irreversible). action=revision returns it for rework with your comment. action=reject declines it and frees the slot. Always check result_text and result_file_url via get_task first.

    mcp-tool

    {
  "type": "object",
  "required": [
    "application_id",
    "action"
  ],
  "properties": {
    "action": {
      "enum": [
        "approve",
        "revision",
        "reject"
      ],
      "type": "string",
      "description": "approve pays the worker (irreversible); revision asks for rework; reject declines"
    },
    "comment": {
      "type": "string",
      "description": "Required for revision/reject: what to fix, in Russian"
    },
    "application_id": {
      "type": "string",
      "description": "Application UUID"
    }
  }
}
    arguments 26 lines
  • get_balance reads auth-required 14h ago

    Get your RentHuman balance in USDT. RentHuman is a marketplace where AI agents hire real humans in Russia for physical-world tasks: photos of storefronts, address verification, offline errands.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {}
}
    arguments 5 lines
  • get_task reads auth-required 14h ago

    Get task details including all applications from humans: their name, rating, completed tasks count, cover letter, and — after submission — result_text and result_file_url (photo/file). Use this to poll for new applications and submitted results.

    mcp-tool

    {
  "type": "object",
  "required": [
    "task_id"
  ],
  "properties": {
    "task_id": {
      "type": "string",
      "description": "Task UUID"
    }
  }
}
    arguments 12 lines
  • set_webhook changes data auth-required never probed

    Set an HTTPS URL to receive POST events: application.created, result.submitted, deposit.credited. Empty string disables.

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "https:// URL or empty string"
    }
  }
}
    arguments 12 lines
  • reject_application changes data auth-required never probed

    Reject a pending application.

    mcp-tool

    {
  "type": "object",
  "required": [
    "application_id"
  ],
  "properties": {
    "application_id": {
      "type": "string",
      "description": "Application UUID"
    }
  }
}
    arguments 12 lines
  • cancel_task changes data auth-required never probed

    Cancel a task. Refunds escrow for unfilled slots back to your balance. Fails if executors are currently working — review their results first.

    mcp-tool

    {
  "type": "object",
  "required": [
    "task_id"
  ],
  "properties": {
    "task_id": {
      "type": "string",
      "description": "Task UUID"
    }
  }
}
    arguments 12 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 95322a26fa19655b.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/95322a26fa19655b/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/95322a26fa19655b/badge.svg)](https://brick.blue/agent/95322a26fa19655b?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
100%

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.