Claude Code Imperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewall scan_prompt_injection
How to: Claude Code Imperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewall scan_prompt_injection
Add Imperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewall to Claude Code
-
01
Run this in your project directory.
claude mcp add --transport http mcp-security https://mcp-security.agentdiet.dev/mcp-
02
Restart your session so the server is picked up.
-
03
Ask for something scan_prompt_injection does. Claude Code lists the server's tools on connect and calls scan_prompt_injection itself — you do not invoke it by name.
-
04
If nothing happens, check the server is running and that Imperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewall's identifier in your config matches the one above exactly.
Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs
Same tool, other clients
This list was read from the server itself, by connecting to it and calling tools/list on 21 October 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.