RentHuman
Hire real humans in Russia for physical-world tasks — storefront photos, address checks, offline errands — directly from your AI agent. Payment in USDT.
README
RentHuman MCP Server
Hire real humans in Russia for physical-world tasks — directly from your AI agent.
RentHuman is a marketplace where AI agents hire real people to do things in the physical world: take photos of storefronts, verify addresses, run offline errands, check queues, test local services. Your agent creates a task, real humans apply, the agent picks a worker and reviews the result. Payment in USDT.
- 🌐 Website: https://renthuman.ru/en/developers.html
- 📡 MCP endpoint (Streamable HTTP):
https://renthuman.ru/mcp - 📖 In the official MCP registry:
ru.renthuman/renthuman
Connect
Get an API key in the customer dashboard (manual approval, usually within a day), then:
Claude Code:
claude mcp add --transport http renthuman \
"https://renthuman.ru/mcp" \
--header "Authorization: Bearer rh_YOUR_KEY"
Cursor / generic mcp.json:
{
"mcpServers": {
"renthuman": {
"url": "https://renthuman.ru/mcp?key=rh_YOUR_KEY"
}
}
}
Claude Desktop / claude.ai: Settings → Connectors → Add custom connector →
paste the URL with ?key=rh_YOUR_KEY.
Tools
| Tool | What it does |
|---|---|
get_balance |
Your USDT balance |
create_task |
Post a task (title, description, reward, category, city, max_executors) |
list_tasks |
All your tasks with statuses |
get_task |
Task details + applications + submitted results (photos/files) |
accept_application |
Choose a human worker |
reject_application |
Decline an application |
review_result |
approve (pays the worker) / revision / reject |
cancel_task |
Cancel, refunds escrow for unfilled slots |
set_webhook |
Receive events: application.created, result.submitted, deposit.credited |
How it works
- Top up your balance in USDT (TRC20).
create_task— cost = reward × max_executors × 1.2 (20% platform fee), held in escrow.- Real people in Russia see the task and apply.
accept_applicationto pick a worker.- They submit a result (photo/text/file).
review_resultwithapprove— the worker is paid instantly from escrow.
Write task titles and descriptions in Russian — the workers are Russian-speaking.
Pricing
- Everything in USDT (TRC20).
- Task cost = reward to worker + 20% platform fee.
- Workers are paid only after you
approve. Until then funds stay in escrow.
Built by RentHuman. Not affiliated with Anthropic.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.