Skip to main content
Glama

LLM Red-Team Scanner

by dev.workers.manhliemcn4euwlu.llmrt-companion
OverviewDiscussionsAdmin

Server Details

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

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
71.0% over 37 days
Last Tested
Transport
Streamable HTTP
URL

TDQS

A4.2/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a clearly distinct role: pricing lookup, purchase procedure, scan initiation, and result polling. There is no meaningful overlap between them.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern: get_ for retrieval/information and run_ for the one action. The naming makes each tool's behavior predictable.

Tool Count5/5

Four tools is well-scoped for a focused scanner server. Each tool maps to a necessary step in the free-scan and paid-upgrade workflow.

Completeness5/5

The surface covers the full lifecycle: start a free scan, poll for its result, inspect PRO pricing, and obtain the autonomous purchase procedure. There are no obvious dead ends or missing operations for the stated purpose.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 4 tool updates
    • First observedget_pricing
    • First observedget_purchase_flow
    • First observedget_scan_result
    • First observedrun_free_scan

Related MCP Connectors

Related MCP Servers

  • agent-audit

    piiiico
    A
    license
    Not graded
    quality
    B
    maintenance
    Security scanner for MCP servers. Detects prompt injection, command injection, auth bypass, and excessive permissions across tools, resources, and prompts.
    46 npm
    2
    MIT

  • inkog

    inkog-io
    A
    license
    A
    quality
    B
    maintenance
    Security co-pilot for AI agents. Scans for vulnerabilities like prompt injection, infinite loops, and token bombing in AI Agents, audits MCP servers, verifies AGENTS.md governance, and generates EU AI Act compliance reports.
    10
    160 npm
    3
    Apache 2.0

  • AgentShield

    elliotllliu
    A
    license
    Not graded
    quality
    C
    maintenance
    Full-stack security for AI agents — static analysis + MCP runtime interception. 31 rules detect prompt injection, data exfiltration, backdoors, tool poisoning, and cross-file attack chains. Includes MCP proxy for real-time blocking, Python AST taint tracking, multi-language injection detection (8 languages), and AI-powered deep analysis. Free, offline, zero-config.
    24 npm
    15
    MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources