Imperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewall for ChatGPT

dev.agentdiet/mcp-security

Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.

client:ChatGPT transport:streamable-http tools:2

Install Imperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewall in ChatGPT

Settings → Connectors → Advanced → Developer mode

https://mcp-security.agentdiet.dev/mcp

Custom connectors are a paid-plan feature and take a remote URL only. ChatGPT cannot run a packaged server locally. ChatGPT docs