LLM Security Scanner

Overview

LLM Security Scanner is a Model Context Protocol server that runs security probes against LLM agents, testing for injection vulnerabilities, jailbreak attempts, tool abuse, and evaluating guardrails. Any MCP-compatible AI assistant can invoke its tools to assess agent resilience during conversations or agent runs.

The server runs remotely at https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-security with no authentication required and no local installation needed. Current release is v1.1.0. Visit https://llmrt-companion.manhliemcn4euwlu.workers.dev/agent for more information.

LLM Security Scanner is categorized as AI & Agents on mcp.site and integrates with all MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this project, claim your listing to verify ownership and keep information up to date.

Installation

Settings → Connectors → Add custom connector
Name: LLM Security Scanner
URL:  https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-security