SkillAvatars
Model Context Protocol servers - tools, resources, and prompts for Claude and other AI assistants.
Start Better
MCP discovery works better when people begin from a job to be done. Route them into a scene, a curated stack, or a high-signal tag before they start scanning tool cards.
Scenes
Stacks
Popular tags
Showing 24 of 286 MCP tools
Cryptographic proxy and credential vending for LLM applications. Zero secrets on disk. mTLS everywhere. Apache 2.0.
Organize, secure, and find Claude Code skills in one vault for easy reuse
Security tripwires for AI agents. MCP tools that detect prompt injection, credential theft, and unauthorized tool calls in real time. Open source, zero dependencies, works with Claude Desktop, Cursor, Windsurf, VS Code, and Claude Code.
🛡 Enhance OpenClaw security by auditing, monitoring, and protecting your installation with a reliable all-in-one tool.
Sync Claude CLI credentials to OpenCode with cross-platform multi-account support, quota tracking, rotation, and one-command switching
Provide high-speed real-time packet capture and network analysis with Rust-powered parsing and threat detection for efficient MCP server use.
Scan and analyze MCP servers to assess AI agent security risks and provide clear safety scores updated daily.
An AI first penetration testing toolkit ✨
Production-ready MCP provider for SQL databases with unified AI agent interface, supporting MySQL, MariaDB, PostgreSQL, and SQLite with secure credential management and comprehensive query tools.
Practical audit tools and controls for securing MCP servers and agentic AI tool access.
JFrog Plugin for seamless integration to Opencode
MISP (Malware Information Sharing Platform) MCP server with built-in prompt injection defense via prompt-defense-audit
rldyour AI CLI configuration for OpenCode: local plugins, MCP/LSP, permissions, commands, agents, browser/design workflows, and security review.
Order from Swiggy right from your terminal
Offline methodology engine and payload workshop for authorized penetration testing, CTF, security research, and education via MCP. STDIO or Streamable HTTP.
Knowledge Vault MCP Server — structured wiki with BM25 search, typed knowledge graph, batch validation, and companion skills for autonomous knowledge compilation.
Secure MCP (Model Context Protocol) server with role-based permission management, elicitation-based user approval workflows, and full audit logging — built with FastMCP, Python & Gradio
Reference MCP security lab: toxic tool metadata, multi-server mcp.json harness for static scan, localhost AAuth fixtures, YARA (OWASP Agentic ASI01–ASI10). Stress-test MCPShark and similar tools—not for production.
MCP server for automated environment security auditing. Scans for credential exposure, configuration drift, and misconfigurations.
It's a Python-based CLI security scanner built specifically to audit MCP (Model Context Protocol) servers — the integration layer that connects AI assistants like Claude to external tools. Since MCP servers run with real system access, a malicious or poorly written one can be catastrophic.
One command. Zero cloud. Your docs stay private.
ESLint rules to detect prompt-injection vectors in Model Context Protocol server code
Local-first markdown knowledge vault for Claude Code — semantic search, chunk retrieval, graph-aware context via MCP tools
MCP & Agent Skill Security Scanner - OWASP Agentic AI Top 10 + MCP Top 10 Compliant. 21 security rules scanning MCP server configurations and SKILL.md packages for vulnerabilities.