Hey Product Hunt! 👋 I'm Amir, and I built ContextGuard after discovering that 43% of MCP servers have critical security vulnerabilities. ## What is MCP? Model Context Protocol is the new standard that lets AI assistants like Claude access external tools, filesystems, and APIs. Think of it as a plugin system for AI. ## The Problem When you give AI assistants access to your data through MCP servers, you're opening up serious attack vectors: - Prompt injection attacks - API key leakage - Path traversal exploits - Unauthorized data access Most developers building MCP servers don't have security expertise, and there wasn't an easy way to add protection. ## The Solution: ContextGuard A zero-config security wrapper that sits between your AI client and MCP server: ✅ Detects 8+ prompt injection patterns in real-time ✅ Scans for sensitive data (API keys, passwords, SSNs) ✅ Prevents path traversal attacks ✅ Rate limiting to prevent abuse ✅ Comprehensive JSON logging ✅ <1% performance overhead ✅ Zero code changes needed ## How It Works ```bash npm install -g contextguard contextguard --server "node your-mcp-server.js"

ContextGuard

Open-source security monitoring for MCP servers

Open-source security monitoring for MCP servers