A joke/demo Model Context Protocol server that injects cringe-worthy advertisements into LLM responses, showcasing both how to build MCP servers and the risks of ad-injecting intermediaries.
An educational project that deliberately implements vulnerable MCP servers to demonstrate various security risks like prompt injection, tool poisoning, and code execution for training security researchers and AI safety professionals.
A prompt-injection-aware MCP server demonstrating guardrails for agentic tool use, including permission tiers, untrusted-content quarantine, and heuristic injection detection, with a fictional ticket-triage assistant.