Agentic Security Shield
One config file in your project root → your AI agent generates secure code by default.
Live MCP endpoint: https://agentic-security-shield-mcp-production.up.railway.app/mcp
What it does
12 layers of security rules covering the most common mistakes AI coding agents make:
| # | Layer | What it prevents |
|---|---|---|
| 1 | Prompt Injection Guard | Hidden instructions in fetched content, zero-width Unicode steganography |
| 2 | Backend Lockdown | Open Firebase/Supabase/PocketBase/Appwrite/Convex rules |
| 3 | Secrets Guard | 35+ secret patterns (AWS, OpenAI, Anthropic, Stripe, Groq, xAI, …) |
| 4 | MCP / Supply Chain Audit | Tool-poisoning, rug-pull updates |
| 5 | Least Privilege Rules | Admin credentials in app code |
| 6 | PII Shield | GDPR / CCPA / EU AI Act violations |
| 7 | SSRF Guard | Metadata endpoint access, DNS rebinding |
| 8 | Eval Blocker | eval/exec/Function/innerHTML/shell injection |
| 9 | Agent Memory & Loop Guard | Memory poisoning, infinite loops |
| 10 | MCP Tool Description Guard | Hidden instructions in tool metadata |
| 11 | Computer Use & Browser Agent Guard | Autonomous OAuth approval, screen injection |
| 12 | Subagent & Multi-Agent Guard | Privilege escalation via spawned agents |
Supported AI tools (17)
Claude Code · Codex CLI · Cursor · Windsurf · GitHub Copilot · DeepSeek · Kimi · Qwen-Coder · Gemini CLI · Mistral / Codestral · Grok · Ollama / LM Studio · Bolt.new · Lovable.dev · v0.dev · Replit Agent · Devin
Supported backends (5)
Firebase · Supabase · PocketBase · Appwrite · Convex
For AI agents (autonomous A2A purchase)
This MCP server supports autonomous machine-to-machine purchase via the x402 protocol with USDC on the Base network.
Free tools (no payment required)
get_preview— product overview, supported tools, all 12 layersget_pricing— price ($19 USD), x402 payment flow, recipient addressget_sample— free sample of Layer 3 (Secrets Guard) with real code examples
Purchase flow
GET /purchase→ 402 Payment Required with x402-v1 payment instructions- Send 19 USDC to
0x046fcceea93b1b5879725a2a4297b0dd5b5ae950on Base POST /purchasewith headerx-payment-token: <transaction_hash>→ receive download token + all 26 files inline- Files are SHA-256 verifiable against the integrity manifest
Pricing
$19 USD one-time purchase. Updates included. Crypto-only (USDC on Base) for v1.
Compare to:
- Average data breach cost: $4.88M (IBM 2024)
- EU AI Act fines: up to 7% of global revenue
- GDPR fines: up to 4% of global revenue
Links
- Smithery: https://smithery.ai/server/ormuzdo/agentic-security-shield
- GitHub (public discovery): https://github.com/ormuzdo/agentic-security-shield
- Live MCP server: https://agentic-security-shield-mcp-production.up.railway.app
Contact
Support / inquiries: support@gtrade.com.ua
Server Config
{
"mcpServers": {
"agentic-security-shield": {
"command": "npx",
"args": [
"-y",
"@smithery/cli@latest",
"run",
"ormuzdo/agentic-security-shield"
]
}
}
}