1,221 servers
a proactive security and stability guardrail for your AI coding agents (Claude Code, Cursor, Antigravity, etc.). It prevents production breakages by confronting proposed code changes with a massive, real-time database of global incidents, edge cases, and security breaches.
MCP (stdio JSON-RPC) server for Pentool AI — local LLM assistant for pentest
Remote proxy for Model Context Protocol servers with mTLS (mutual TLS) client certificate authentication support.
Test MCP server: cloud ops (deliberate security issues for MCPSafe e2e testing)
Shared utilities for token-efficient MCP servers — RBAC, audit logging, lean response shaping, TLS config
Pre-install trust assessment for MCP servers — VirusTotal for the MCP ecosystem
IMAP/SMTP 信箱 MCP server — 把任意標準信箱（Gmail/Outlook/自架…）包成 MCP tools；支援本地 stdio 與遠端 HTTP/OAuth 部署
A sandboxed MCP tool for reverse engineering with multiple tool integrations
Security scanner for MCP (Model Context Protocol) server configurations and AI agent tool permissions.
MCP Tool Poisoning Scanner — Defensive scanning + offensive pentest tooling for MCP servers. Maps to OWASP MCP Top 10.
MCP server for auditing Terraform state files for security misconfigurations
Open-source, self-hosted Zero Trust policy enforcement layer for MCP servers.
Credential injection middleware for FastMCP servers — keeps secrets out of the LLM
MCP server for Azure Entra PIM — list eligible assignments and activate group/role assignments
Model Context Protocol server for Cyberbro IOC analysis and enrichment
Scan MCP configs for 30+ CVEs, prompt injection, tool poisoning; validate OAuth configs
MCP-Bastion security middleware for AWS Bedrock — prompt injection, PII, and rate-limit protection for cloud AI agents
SquatGuard MCP Template for Python
Authorization for MCP Python servers: OAuth resource server, policy, and permission-gated capabilities
MCP server exposing Capstone 5.0.7 disassembly framework