LLM Red-Team Scanner
Server Details
LLM agent security review: live injection/jailbreak probes plus a static audit of missing guardrails
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 5 tools
The scan lifecycle tools are distinct, but get_pricing and get_purchase_flow overlap around payment and purchase information, which could cause misselection. validate is also domain-adjacent rather than core scanner functionality, making its role in this set less immediately clear.
Most tools follow a clear verb_noun pattern: get_pricing, get_purchase_flow, get_scan_result, run_free_scan. The bare validate tool is a minor deviation but remains readable.
Five tools is a well-scoped size for a focused scanner service. Each tool covers a specific step: pricing, purchase flow, free scan, polling results, and validation.
The surface covers free scanning, result polling, and purchase details, but lacks explicit paid scan execution or broader scan management such as listing, cancelling, or retrieving PRO reports directly. The unrelated validate tool does not fill those gaps.
Available Tools
5 toolsget_pricingAInspect
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.
Inputs: no named parameters.
get_purchase_flowAInspect
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 fallback).
Inputs: no named parameters.
get_scan_resultAInspect
Poll a scan by job id (returned by run_free_scan) until status=done.
Inputs: job_id (required).
run_free_scanAInspect
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 (2) a deterministic static audit of which guardrails the spec text itself is missing. Returns a 0-100 risk score, per-finding evidence, and a paste-ready guardrail sentence for each gap.
Inputs: spec (required).
validateAInspect
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 only machine-checkable criteria (json_schema / contains / fields); a task with no such rule is accepted, because rejecting needs evidence.
Inputs: input, title, result, taskId, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
AI agent security audit: red-team probes plus missing-guardrail review with fixes.
LLM agent security scan: injection, jailbreak, tool abuse probes plus guardrail audit.
Prompt injection and system-prompt extraction testing for LLM agents. Free 8-probe sample.
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
Related MCP Servers
- AlicenseAqualityDmaintenanceSecurity scanning, prompt injection detection, secret leak detection, and agent permission auditing for AI agent workflows.861 npmMIT
- AlicenseBqualityCmaintenanceWAF for AI agents — block prompt injection before it reaches the LLM.591 PyPIMIT
- AlicenseNot gradedqualityBmaintenanceEnables real-time injection fuzzing and canary-based exfiltration detection over untrusted prompts, RAG context, and agent actions, with entropy analysis, outbound channel interception, least-privilege sandboxing, and cryptographic audit proofs.7MIT
- AlicenseNot gradedqualityCmaintenanceA security interceptor for AI agents that mitigates prompt injections and data loss in autonomous workflows.547 npm1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.