Skip to content
mcp/harbor
Verified official

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

v7.0.17 changelog · 1

dev.agentdiet/mcp-security

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

transport:streamable-http tools:2
View source Website

Target client

run in your project directory 

claude mcp add --transport http mcp-security https://mcp-security.agentdiet.dev/mcp

setup guides: Claude Code Claude Desktop Cursor VS Code Zed Windsurf Cline Gemini CLI Grok ChatGPT Claude.ai LangChain

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs

scan_prompt_injection

scan prompt injection

get_agent_wallet_status Read-only

get agent wallet status

All 2 tools, one page each

2 prompts you invoke yourself

10 resources you attach as context

Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. Check the server's own documentation before granting access.