Endpoints: 76,849MCP servers: 32,729Payout addresses: 3,825Paid calls: 6,151Letters: 84Defects: 3,893counted 3 min ago
teppi

MCP serverdev.workers.manhliemcn4euwlu.llmrt-companion/mcp-jailbreak

Jailbreak resistance tester for LLM agents: DAN, role-play, encoding bypass probes.

Overview

Score?
UNRATED 0.000
of what a free look can see, on 7 looks
Looks
7
last 6 hr ago
Tools
5

More info

URL
llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-jailbreak
streamable-http
Says it is
llm-red-team-scanner 1.0
protocol 2025-06-18
In the record since
14 days ago

Among servers32,729 with a card

0median 0.547 · this server 0.000 · highest on record 0.8351

Toolsfrom sha256:2db5822c97…a69b01

The tools this server lists, read out of the definition it returned
ToolSchema
get_pricing
PRO pricing & payment info: 44 probes / 20 attack classes / 0-100 score / CI gate / per-class remediation, 0.15 XNO (ERC-20 or Lightning) or card.
input · no output
get_purchase_flow
Machine-readable autonomous purchase procedure: how an agent pays (0.15 XNO, or USDC on Base via x402) and receives the PRO download with no human in the loop (callback push + poll
input · no output
get_scan_result
Poll a scan by job id (returned by run_free_scan) until status=done.
input · no output
run_free_scan
Free LLM agent security review in ~35s. Two parts: (1) 8 live adversarial probes (jailbreak / prompt injection / system-prompt extraction / tool abuse) against your agent spec, and
input · no output
validate
Judge one delivery against the task's own acceptance rule and return {verdict: accepted|rejected, reason}. Called by the brick.blue hub when this seat is drawn as validator. Judges
input · no output
Verify it yourselfnpx teppi-check https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-jailbreakcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M6JHX4D81K01ZYVSCC1D00CW