MCP Shield

v1.0.0โ€ขSecurityโ€ขstable

๐Ÿ“‡ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - Security scanner for MCP servers. Detects backdoors, exfiltration code, obfuscation,

ai-agentai-securityclaudecli-toolcybersecurity
Share:
553
Stars
0
Downloads
0
Weekly
0/5

What is MCP Shield?

MCP Shield is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ๐Ÿ“‡ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - security scanner for mcp servers. detects backdoors, exfiltration code, obfuscation,

๐Ÿ“‡ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - Security scanner for MCP servers. Detects backdoors, exfiltration code, obfuscation,

This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP protocol support

Use Cases

Scan MCP servers for backdoors, exfiltration code, and obfuscation.
Detect security vulnerabilities in AI agent integrations.
muhannad-hash

Maintainer

LicenseMIT License
Languagetypescript
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp-shield

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MCP Shield

MCP Shield is a security scanner that protects your AI agent setup by analyzing MCP servers before you install or run them. It detects backdoors, exfiltration code, obfuscation techniques, hidden prompt injections, and supply-chain risks embedded in npm MCP packages or local server directories. Developers and security-conscious teams use it to vet third-party MCP servers and catch malicious patterns that could compromise their Claude or other LLM workflows.

Prerequisites

  • Node.js 16 or later installed
  • An MCP client such as Claude Desktop or the Claude CLI
  • npx available on your PATH (comes with Node.js)
  • Internet access to check npm package trust scores and CVE data
1

Install MCP Shield via npx

Run MCP Shield directly with npx โ€” no global install required. The command launches the MCP server process that your client will connect to.

npx mcp-shield
2

Add MCP Shield to your Claude CLI

Register the server with the Claude CLI so it is always available as a tool when you open a session.

claude mcp add mcp-shield -- npx mcp-shield
3

Configure in Claude Desktop

Add the server block to your Claude Desktop configuration file at ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or the equivalent path on Windows/Linux.

{
  "mcpServers": {
    "mcp-shield": {
      "command": "npx",
      "args": ["mcp-shield"]
    }
  }
}
4

Scan an npm MCP package before installing

Ask your AI assistant to run the scan_package tool against any npm package you are considering. MCP Shield downloads and analyzes the package code for malicious patterns.

5

Scan a locally cloned MCP server

Use scan_directory to inspect a MCP server repository you have already cloned. Provide the absolute path to the directory.

6

Audit your installed MCP servers

Ask the assistant to audit all currently configured MCP servers. MCP Shield runs check_prompt_injection on tool descriptions and audit_supply_chain for trust score and CVE data.

MCP Shield Examples

Client configuration

Claude Desktop config block to enable MCP Shield.

{
  "mcpServers": {
    "mcp-shield": {
      "command": "npx",
      "args": ["mcp-shield"]
    }
  }
}

Prompts to try

Example queries you can ask once MCP Shield is connected.

- "Scan the npm package 'xyz-mcp-server' before I install it"
- "Scan the MCP server I cloned at ~/projects/some-mcp"
- "Check this tool description for prompt injection: <paste text>"
- "What's the trust score for 'popular-mcp-tool' on npm?"
- "Audit all the MCP servers I have installed"

Troubleshooting MCP Shield

npx mcp-shield fails with 'command not found' or network error

Ensure Node.js 16+ is installed and npx is on your PATH. Run 'node --version' to verify. If behind a proxy, set the HTTPS_PROXY environment variable before running npx.

Scan results show false positives on legitimate packages

Review the specific patterns flagged in the scan output. MCP Shield heuristics may trigger on obfuscated but benign minified code. Cross-check the package source on GitHub before dismissing a warning.

audit_supply_chain returns no CVE data

MCP Shield relies on npm registry metadata and external CVE feeds. Ensure you have internet connectivity and that the package name is spelled correctly. Brand-new packages may have no historical data yet.

Frequently Asked Questions about MCP Shield

What is MCP Shield?

MCP Shield is a Model Context Protocol (MCP) server that ๐Ÿ“‡ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - security scanner for mcp servers. detects backdoors, exfiltration code, obfuscation, It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MCP Shield?

Follow the installation instructions on the MCP Shield GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with MCP Shield?

MCP Shield works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MCP Shield free to use?

Yes, MCP Shield is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

MCP Shield Alternatives โ€” Similar Security Servers

Looking for alternatives to MCP Shield? Here are other popular security servers you can use with Claude, Cursor, and VS Code.

Casdoor

โ˜… 13.6k

An open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD

ghidraMCP

โ˜… 9.0k

An Model Context Protocol server that enables LLMs to autonomously reverse engineer applications by exposing Ghidra's decompilation and analysis tools. It allows AI agents to list code structures, rename methods, and analyze binaries directly through

HexStrike AI

โ˜… 8.9k

HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly b

IDA Pro MCP

โ˜… 8.7k

Enables AI-assisted reverse engineering in IDA Pro by providing tools to analyze binaries, decompile functions, manage comments, search patterns, and interact with the IDA database through natural language.

Anthropic Cybersecurity Skills

โ˜… 6.6k

754 structured cybersecurity skills for AI agents ยท Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF ยท agentskills.io standard ยท Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platform

Hooker

โ˜… 5.1k

๐Ÿ”ฅ๐Ÿ”ฅ hooker is a Frida-based reverse engineering toolkit for Android. It offers a user-friendly CLI, universal scripts, auto hook generation, memory roaming to detect activities/services, one-click SOCKS5 proxy setup, Frida JustTrustMe, and BoringSSL u

Browse More Security MCP Servers

Explore all security servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-shield": { "command": "npx", "args": ["-y", "mcp-shield"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide โ†’

Ready to use MCP Shield?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides