MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
An AI security platform designed to protect autonomous agents and MCP-connected tools through runtime security enforcement, risk assessment, policy-based access control, human approvals, and audit log
MCPLink only★ 1Few stars
The Claude code plugin that can aid during bug bounty or any security assessment by collecting knowledge from prior assessments and utilize that knowledges in your current context.
SkillLink only★ 2Few stars
Claude-skill die sterke toets- en examenvragen schrijft, gekoppeld aan leerdoelen en denkniveaus, met sleutel en feedback per optie.
SkillLink onlyFew stars
AI agent security reference and MCP: DASF risks, controls, audit checklists, prompt injection and RAG security.
MCPLink onlyFew stars
Autonomous Multi-Agent Security Orchestration, Zero-Read Fast-Path, and Unrestricted Security Audit Plugin for Google Antigravity 2.0
SkillLink onlyFew stars
🛡️ Operational security skills for AI agent runtimes — safe installs, silent-failure detection, rollback. War-story driven, SKILL.md standard
SkillLink only★ 1Few stars
Claude skill: interactive security check of a Claris FileMaker Server you own or manage, with a plain-English findings report.
SkillLink only★ 1Few stars
软件工程安全防破解：LLVM/虚拟化、服务端鉴权、心跳、防重放与跨平台完整性 Agent Skill
SkillLink only★ 1Few stars
Security skill for coding agents: 29 official standards (OWASP, NIST, MITRE, CWE, CVSS 4.0), code and dependency audits with cited sources
SkillLink only★ 2Few stars
Gibwork Solana Security Agent: Non-web CLI & MCP server for token risk analysis and bounty escrow auditing
MCPLink onlyFew stars
Security briefing notes for our team's adoption of the Model Context Protocol (MCP), including supply-chain advisory highlights.
MCPLink onlyFew stars
Hands-on labs for securing AI agents and agentic protocols based open standards
MCPLink only★ 1Few stars
MCP Security Sanitizer is a Python-based MCP server that helps redact common API keys, secrets, and personally identifiable information from text. It also provides a risk-audit tool and connects to MC
MCPLink onlyFew stars
A small MCP server and interactive LangChain/Groq chatbot. The server exposes local regex-based tools for redacting common secrets and personally identifiable information (PII), and the client sanitiz
MCPLink onlyFew stars
Preproduction security audits for coding agents. Adaptive scoping, 167 controls across 35 security domains, repository and CI/CD review, dependency analysis, and Markdown reports with evidence graphs
SkillLink onlyFew stars
Bidirectional in-memory sensitive vault and surrogate token masker protecting credentials in LLM prompt exchanges
MCPLink only★ 7
Bidirectional in-memory sensitive vault and surrogate token masker protecting credentials in LLM prompt exchanges
SkillLink only★ 7
RedVector AI - AI-powered penetration testing and cybersecurity automation framework for security researchers and ethical hackers.
MCPLink only★ 2Few stars
Security for AI agents that act. The agent proposes. ExecBound decides.
MCPLink onlyFew stars
Static security scanner for Claude Code skills. Finds exfiltration, credential access, hardcoded secrets, obfuscation and risky dependencies.
SkillLink onlyFew stars
Enhanced distribution of HOL Guard: AI agent runtime security with MCP server, African threat intelligence, benchmarks, and architecture visualization
MCPLink onlyFew stars
800 tool-description injection attacks (MCPTox) against Claude Opus 5, Opus 4.8, Sonnet 5 and Haiku 4.5. Deterministic scorer validated against the benchmark's 7,368 human labels.
MCPLink onlyFew stars
Proof of concept for Delegated Intent Verification (DIV): deterministic checks on whether a coding agent’s actions are justified by the developer’s original request. A simulated agent trace shows a po
MCPLink onlyFew stars
77 defensive security skills for Claude Code: drop-in SKILL.md files for detection engineering, incident response, threat hunting and hardening
SkillLink onlyFew stars
Who stands behind it
