dev.workers.manhliemcn4euwlu.llmrt-companion/llm-red-team-scanner·AI & LLMs

LLM Red-Team Scanner

35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.

Stars
—
Version
1.0.0
License
—
Review
Passed
Registry update
Sep 14, 2026

Connect

remote
Terminal
$claude mcp add --transport http llm-red-team-scanner https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp

Headers

Nothing to configure — it works as is.

Security review

Review passed

Reviewed 1h ago.

tools
4 tools scanned
metadata
scanned

No findings.

Tools

4
  • 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.

  • get_scan_result

    Poll a scan by job id (returned by run_free_scan) until status=done.

  • get_pricing

    PRO pricing & payment info: 24 probes / 9 attack classes / 0-100 score / CI gate, 3 USDT (ERC-20 or Lightning).

  • 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).

More in AI & LLMs

Listing from the official MCP Registry.