Scan AI agent skills, plugins, MCP servers, and CLI tools (npm/PyPI/Go, cargo, release binaries, curl|bash installers) for malicious code before installation - one scan, every agent (Claude Code, Code
VMware NSX security: DFW policies and exclusions, groups, tags, Traceflow, IDPS — 22 MCP tools.
A security graph reporting tool, with agentic workflows, AI chat assistant, and automation for CVE remediation and graph data population.
KhaosMCP is a local-first, agent-operated pentest platform using AI via MCP. It connects the external operator to the complete assessment cycle: scoping, supervised execution, integrations, evidence g
OS keychain secrets for AI coding agents, over MCP. Native vault storage (macOS Keychain, Linux Secret Service, Windows Credential Vault), policy-governed access, audit log — CLI + 44 MCP tools.
Open framework for empirical AI visibility benchmarks, multi-model provider observation, and reproducible GEO research.
Cross-framework MCP server and CLI for MITRE ATT&CK, D3FEND, ATLAS and F3, with provenance on every link. Renders D3FEND CAD, Attack Flow, Navigator and Mermaid diagrams.
A small web app + local API for tuning Azure WAF false positives without paying Log Analytics prices.
Veto MCP — gives every major AI CLI (Claude Code, Codex, Gemini, Cursor, Windsurf) a council of 49 specialist agents + 93 tools. Deterministic-first, self-learning, no API keys.
MCP server that checks dependencies against CVE databases before your AI coding agent installs them. Blocks vulnerable and hallucinated packages in real time.
A modular MCP server offering extensible penetration testing tools for network scanning, web security, and reconnaissance.
Intercept & tamper proxy for MCP traffic — X-ray and rewrite the JSON-RPC between an AI agent and its MCP servers. Burp Suite for AI agents. Authorized testing only.
CTPAX - reverse-engineering MCP server: Ghidra, x64dbg, Nuclei, Metasploit, Wireshark, forgery & license-gate tooling (248 tools)
RedQuanta MCP transforms penetration testing into an intelligent, automated, and secure process. Built specifically for LLM integration and professional security teams, it provides enterprise-grade se
**Adversarial MCP integration testing toolkit for Salesforce — seeds ~270 records across Account, Contact, Case, and Outreach Log with 14 attack payload categories including prompt injection, honeytok
Multi-instance IDA Pro MCP server — analyze multiple binaries simultaneously through a single MCP endpoint.
OAuth 2.1 authorization and MCP server on Vercel for MCP clients with real-time analytics and threat detection
MCP server for finding out what level of vulnerability a CVE is
Secure middleware server implementing Model Context Protocol (MCP) over SSE with JWT authentication. Enables standardized communication between AI tools and clients with dynamic tool registration, req
A Claude Code skill that audits your configuration for malicious hooks, MCP servers, and suspicious commands
A MCP server that enables LLMs to interact with MISP (Malware Information Sharing Platform) instances for threat intelligence operations.
Weavatrix Online extension: guarded sync, advisories, malware review, architecture contracts.
Attacking an MCP server to demonstrate the need of stateful auth.
oh-my-triage is an open-source MCP server and visual setup tool that connects code scanning findings from SonarCloud, Socket.dev, GitHub Code Scanning, SARIF, Snyk, Semgrep, and more to AI agents for
Google OAuth-enabled MCP server with built-in analytics tracking for Cloudflare Workers
Web-based tool for testing MCP server OAuth compliance with RFC 9728, RFC 8414, RFC 7591, and OAuth 2.1
Security MCP server that turns your AI into a penetration tester. 20 tools, 100 best practice guides, 47 vulnerability patterns. Connect to Claude, Cursor, or any MCP client.
Rack/Roda-compatible resource-server toolkit for Oauth2.1 MCP Auth
Self-hosted OAuth 2.1 / OpenID Connect server — passkeys, dynamic client registration, RFC 8707 resource indicators, MCP authorization, SCIM, SAML. Auth0/Clerk alternative.
86-tool OSINT MCP server with private evidence graphs, image analysis, reverse search, and person dossiers.
The Model Context Protocol (MCP) represents a significant advancement in AI system integration, but with it comes a new landscape of security challenges. This repository provides a comprehensive guide
Security pentesting MCP Server with 89 tools across 10 categories. Windows/WSL bridge for Kali tools integration with Claude.
a2a and mcp server with spring security , secure your agent with spring based security features
A dockerized Pentest-Suite capable of running AI-Powered full security checks .
Minimal example of an OAuth 2.1 Authorization Server (FastAPI) and a separate Resource Server (FastMCP) aligned with MCP protocol revision 2025‑06‑18
Library containing OAuth Dynamic Client Registration (DCR) functionality for MCP servers
Gesamtes Verzeichnis
IAM, Scanning und Secrets. 1,343 Server, die meistgenutzten zuerst. Jeder öffnet die Seite des Herausgebers.