広告掲載
MCP.so
ログイン

Shield MCP Server

@modelShield

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

modelShield

Shield MCP Server について

A shield for logging, deep debug and sanitization for MCP servers at development stage

#mcp#security#middleware

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": {
    "shieldmcp": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

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。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Shield MCP?

Shield MCP is a security middleware for Model Context Protocol (MCP) servers. It enhances security and monitoring capabilities—like access control, output sanitization, and rate limiting—without modifying the official MCP SDK. It is designed for developers who want to secure and audit MCP tool calls following best practices.

How to use Shield MCP?

Install via pip (Python 3.8+ required), then import the decorator and helpers. Decorate your MCP tool functions with @secure_tool, passing an allowed tools whitelist, an optional sanitizer function, user/session IDs, and rate limit configuration. The middleware automatically enforces access control, sanitizes outputs, logs calls, and applies rate limits.

Key features of Shield MCP

  • Whitelist-based tool access control
  • Configurable result sanitization (text length, sensitive patterns)
  • Structured audit logging via structlog
  • Token‑bucket rate limiting (requests per minute, burst size)
  • Standardized error handling and formatting
  • Compatible with MCP Inspector

Use cases of Shield MCP

  • Restrict which tools a client can call in a multi‑user MCP server
  • Sanitize tool outputs to remove credit card numbers or email addresses
  • Log all tool invocations with user and session IDs for compliance
  • Prevent abuse by throttling requests with configurable rate limits
  • Add a security layer to existing MCP tools without modifying their code

よくある質問

1

What are the system requirements for Shield MCP?

Python 3.8 or higher and pip. Virtualenv is recommended for development.

2

Does Shield MCP modify the MCP SDK?

No. It works as a middleware layer that intercepts and secures tool calls without altering the official SDK.

3

What logging library does Shield MCP use?

It uses structlog for structured, production‑ready audit logging.

4

Can I use Shield MCP with the MCP Inspector?

Yes, Shield MCP is designed to be fully compatible with the MCP Inspector tool.

5

How do I define which tools are allowed?

Pass a set of allowed tool names to the `@secure_tool` decorator’s `allowed_tools` parameter. Only tools in that whitelist will be permitted.

コメント

「その他」の他のコンテンツ

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K

Maestro

mobile-dev-inc

Painless E2E Automation for Mobile and Web

14.8K

The Living Bread

The Living Bread

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w

Senso MCP for Joomla

sensomedia

Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea

Klarix Intelligence Engine

Klarix

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

広告掲載