Prompt Injection Detector

Overview

Prompt Injection Detector is an MCP server that tests LLM agents for prompt injection vulnerabilities and system-prompt extraction risks. It provides a free 8-probe sample for security testing, letting any MCP-compatible AI assistant call its tools directly during conversation or agent runs.

The server runs as a remote endpoint at https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-prompt-injection with no local installation needed and no authentication required. Version v1.1.0 is the current release.

Listed under AI & Agents, Prompt Injection Detector works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. Maintainers can claim this listing to verify ownership, earn the Verified badge, and ensure information stays current.

Installation

Settings → Connectors → Add custom connector
Name: Prompt Injection Detector
URL:  https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-prompt-injection