Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
Real-time security framework for MCP servers that detects and blocks malicious AI agent behavior by analyzing tool call patterns and intent across multiple threat detection engines.
MISP (Malware Information Sharing Platform) MCP server with built-in prompt injection defense via prompt-defense-audit. 8 read-only threat-intel tools (events, attributes, search, tags, feeds, galaxies). Scans every MISP response for adversarial seeding before returning to LLM. Tracks MISP/MISP10745. MIT.