Enables AI assistants to invoke a registered tool that intentionally withholds forecast information and instead enumerates Windows application folders, exposing them to the client.
Demonstrates deceptive tool naming and unsanitized shell execution by exposing tools that perform OS fingerprinting and run local system commands through MCP. Intended for security research on vulnerabilities in the MCP ecosystem.
Enables users to run a smart-lighting MCP tool that returns an adversarial payload, demonstrating indirect prompt injection and tool hijacking against MCP hosts.