Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "Imperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewall" MCP server from askskill: Run: claude mcp add --transport http 'dev-agentdiet-mcp-security' 'https://mcp-security.agentdiet.dev/mcp'
Strips 85-97% of HTML/DOM bloat into clean Markdown or JSON with cryptographic ROI proof.
Extracts verified emails, social links, 40+ tech stack signals, pricing tiers, and company summar.
Scans live DeFiLlama APYs, TVL depth, and risk-adjusted yield spreads across Base, Arbitrum, Sola.
Queries live HackerNews discussions, front-page velocity, and developer sentiment on any framewor.
Repairs truncated or malformed LLM JSON outputs (trailing commas, markdown fences, single quotes).
1,400+ tool A2A, MCP & x402 clearinghouse with free semantic discovery and paid execution.