mcp-security.agentdiet.dev
LiveMCP ServerImperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewall: Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents. (text from the Official MCP Registry)
Servers On This Host
| Address | Name | Status | Recent Checks OK | Response Time | Tools | Last Checked |
|---|---|---|---|---|---|---|
| https://mcp-security.agentdiet.dev/mcp | Imperium MCP Security — Prompt-Injection, Jailbreak & Tool … | Live | – | 262 ms | 2 | 3 h ago · receipt |
How we check: we connect without logging in and ask for the list of tools. We never send credentials and never pay. Tools that don't state a price are never called; for tools that do, we send at most 2 unpaid calls to read the payment request. We don't make test purchases from MCP servers yet. Signed records: raw data page · free quick check (JSON)
Paid Tools
| Tool | Stated Price | Payment Request Asks | Network | Pays To | Stated Vs Asked |
|---|---|---|---|---|---|
| scan_prompt_injection | – | – | No payment request returned |
From our unpaid check: the tool list, plus at most 2 unpaid calls to tools that state a price, only to read the payment request. We never pay and never call tools that don't state a price. Stated prices are the server's own text or metadata. Full details: free quick check (JSON).