広告掲載
MCP.so
ログイン

Agentic Security Shield MCP Server

@ormuzdo

リポジトリ

基本情報

カテゴリ

開発者ツール

ライセンス

NOASSERTION

トランスポート

stdio

作者

ormuzdo

投稿者

ormuzdo

Agentic Security Shield MCP Server について

Drop-in security configs for AI coding agents — 12-layer protection across 17 tools. Autonomous A2A purchase via x402 (USDC on Base). $19 one-time.

#security#developer-tools#agent-skills#compliance

Agentic Security Shield MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "agentic-security-shield": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli@latest",
        "run",
        "ormuzdo/agentic-security-shield"
      ]
    }
  }
}

Agentic Security Shield MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Agentic Security Shield?

Agentic Security Shield is a drop-in security configuration for AI coding agents that provides 12 security layers and 6 stack-specific hardening patterns to help AI agents generate secure code by default. It is intended for developers using AI coding tools who want to prevent common security mistakes and vulnerabilities.

How to use Agentic Security Shield?

Deploy one configuration file in your project root, then your AI agent will generate secure code by default. The MCP server endpoint is https://agentic-security-shield-mcp-production.up.railway.app; purchase requires sending 19 USDC to a specific address on the Base network and posting the transaction hash.

Key features of Agentic Security Shield

  • Prompt injection guard for fetched content
  • Backend lockdown for Firebase, Supabase, PocketBase, Appwrite, Convex
  • Secrets guard covering 35+ secret patterns
  • MCP and supply chain audit for tool-poisoning defense
  • Least privilege rules with RBAC templates
  • PII shield for GDPR, CCPA, EU AI Act compliance
  • SSRF guard with metadata endpoints and DNS rebinding defense
  • Eval blocker for eval/exec/Function/innerHTML/shell injection
  • Agent memory and loop guard against memory poisoning
  • MCP tool description guard for instruction injection
  • Computer use and browser agent guard for autonomous OAuth
  • Subagent and multi-agent guard for privilege escalation
  • Stack-specific hardening patterns for OAuth, JWT, WebSocket, CORS, file uploads, and more
  • Package hallucination / slopsquatting defense
  • Trojan Source and ANSI escape injection detection

Use cases of Agentic Security Shield

  • Start a project with Firebase, Supabase, PocketBase, Appwrite, or Convex
  • Generate auth, payment, or user-data handling code with AI
  • Deploy AI-generated code to production without manual security review
  • Use Claude Computer Use, ChatGPT Operator, or other browser agents safely
  • Comply with GDPR, CCPA, or EU AI Act requirements in AI-generated code

よくある質問

1

What does Agentic Security Shield cost?

It costs $19 USD, paid via the x402 protocol using USDC on the Base network.

2

How do I purchase Agentic Security Shield?

Send 19 USDC to `0x046fcceea93b1b5879725a2a4297b0dd5b5ae950` on the Base network, then POST to the purchase endpoint with the transaction hash as a header.

3

What backends does Agentic Security Shield support?

It supports Firebase, Supabase, PocketBase, Appwrite, and Convex.

4

What AI tools are supported?

17 tools: 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, and Devin.

5

Is there a free preview or sample?

Yes, three free tools are available without payment: `get_preview` (product overview), `get_pricing`, and `get_sample` (code example of Layer 3 – Secrets Guard).

6

What is the refund policy?

All sales are final because the product is a digital good; refer to the Refund Policy document.

コメント

「開発者ツール」の他のコンテンツ

BetterBugs

BetterBugs

The BetterBugs MCP (Model Context Protocol) enables you to load BetterBugs bug reports (via report links) directly to your preferred AI Agents and developer environments with MCP Client capabilities (such as Cursor, VS C

Yocoolab

Yocoolab

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

1

Capgo MCP

Cap-go

Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app

Zyte MCP

Zyte

Zyte MCP is a remote MCP server available at https://mcp.zyte.com/v1/mcp/, that lets an agent use Zyte on your behalf: to get web pages, to extract data from them, to search the web, and to work with your Scrapy Cloud pr

Pugi

Pugi Inc.

Pugi is an AI product team that builds, checks and publishes websites and apps. Its MCP server gives agents a passive website security check graded A+ to F (headers, TLS, cookies, exposed keys in scripts), free with a no

広告掲載