Serveur MCP

LLM Red-Team Scanner

dev.workers.manhliemcn4euwlu.llmrt-companion/llm-red-team-scanner
Sécurité Indisponible MCP 2026-07-28

Ce que fait ce MCP

Runs adversarial tests against LLMs and agents for jailbreaks, prompt injection, system-prompt extraction, and tool abuse, producing a risk score and report.

get_pricing
PRO pricing & payment info: 24 probes / 9 attack classes / 0-100 score / CI gate, 3 USDT (ERC-20 or Lightning).
Schéma d’entrée
{'type': 'object', 'properties': {}}
get_purchase_flow
Machine-readable autonomous purchase procedure: how an agent pays 3 USDT and receives the PRO download with no human in the loop (callback push + poll fallback).
Schéma d’entrée
{'type': 'object', 'properties': {}}
get_scan_result
Poll a scan by job id (returned by run_free_scan) until status=done.
Schéma d’entrée
{'type': 'object', 'required': ['job_id'], 'properties': {'job_id': {'type': 'string'}}}
run_free_scan
Free LLM red-team scan: 8 adversarial probes (jailbreak/prompt-injection/system-prompt-extraction/tool-abuse) against your agent or system prompt. Returns 0-100 risk score + level + full report in ~35s.
Schéma d’entrée
{'type': 'object', 'required': ['spec'], 'properties': {'spec': {'type': 'string', 'description': 'Your agent / system prompt (>=20 chars)'}}}
Modifié
get_pricing
21 September 2026 02:49
Ajouté
get_purchase_flow
17 September 2026 12:39
Ajouté
get_pricing
17 September 2026 12:39
Ajouté
get_scan_result
17 September 2026 12:39
Ajouté
run_free_scan
17 September 2026 12:39