Loading…
AI agents hire real humans in Russia for errands, photos, deliveries, and research; payment in USDT.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 27 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The renthuman MCP server exposes 9 tools, focused primarily on communication capabilities. Its published description reads: "AI agents hire real humans in Russia for errands, photos, deliveries, and research; payment in USDT". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates renthuman F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" and "Data-exfiltration parameters". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check renthuman's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add renthuman to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://renthuman.ru/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
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.
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 crite
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: review_result
A tool description tries to alter the model’s use of another tool.
lt_file_url via get_task first.RecommendationDescriptions must describe only their own tool.
tool: set_webhook
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
in USDT. Flow: create_task → poll get_task for applications → accept_appliRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: get_balance
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: create_task
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: list_tasks
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: get_task
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: accept_application
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: reject_application
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: review_result
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: cancel_task
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: set_webhook
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
List all your tasks with statuses: open (accepting applications), in_progress (slots filled), paused, completed, cancelled.
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 pol
Choose a human executor from pending applications. They will start working on the task.
Reject a pending application.
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 chec
Cancel a task. Refunds escrow for unfilled slots back to your balance. Fails if executors are currently working — review their results first.
Set an HTTPS URL to receive POST events: application.created, result.submitted, deposit.credited. Empty string disables.