dev.agentdiet/mcp-security

up checked 2026-11-11T04:37:46.334Z

Unclaimed · Unverified

Publisher-provided title

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

Publisher-provided description

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

Summary by lookupd

Scans untrusted pages, emails, and MCP/A2A payloads for prompt injections and returns sanitized text; also reports account usage balances.

Install

Claude Code, remote (streamable-http)

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

Codex, remote (streamable-http)

codex mcp add security --url https://mcp-security.agentdiet.dev/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "security": {
      "url": "https://mcp-security.agentdiet.dev/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

scan_prompt_injection Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized text. WHEN TO USE: Call `scan_prompt_inject
get_agent_wallet_status Inspect an agent's account ledger: remaining free trial calls (out of 5), prepaid USD balance, cumulative spend, total API calls, and total LLM tokens saved. WH

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/dev.agentdiet/mcp-security.svg)](https://lookupd.com/servers/dev.agentdiet/mcp-security)