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
Read-only drift diagnosis and security audit for AI coding agent setups.
MCP server (Python, pip-installable) for image perception via Mistral Pixtral. Structured-JSON output: description, detected_text (OCR), model, latency. Credential-light (MISTRAL_API_KEY only).
AI-native digital forensics & cybercrime investigation platform. 7 MCP servers (Volatility3, Ghidra, Wireshark, OSINT, threat-intel & more) orchestrated by Claude, ChatGPT, or Ollama — fully containerized, chain-of-custody enforced, court-admissible output.
Trust-first daily tool discovery: surfaces vetted dev/CLI tools, filters spam & malware, configurable taste profile.
LLM red-team harness — OWASP LLM Top 10 + MITRE ATLAS attack packs
Deterministic AI security scanner | Prompt injection detection | x402 USDC
MCP server providing security scanning, prompt injection detection, secret leak detection, and agent permission auditing for AI agent workflows
Security gateway for MCP traffic. 5 built-in rules block prompt injection, credential leakage, path traversal, cross-repo exfiltration, and destructive commands. One pip install, zero config.
Shared core library for Flywheel ecosystem. Entity extraction, wikilink matching, SQLite StateDb with eigenvector centrality.
Production-ready n8n workflows for AI automation. 🚀 Includes batch-enrichment, sales-automation, and guardrails, all powered by real-time market demand intelligence.
A safety framework for AI agents that explore the internet. Standing orders, crowdsourced threat intelligence, and real close-call stories.
Protect files with AES-256 encryption and malware analysis in a secure Flask storage platform
Static analysis tool for detecting security vulnerabilities in MCP (Model Context Protocol) server implementations. Uses taint tracking and fixpoint analysis.
Protect AI coding agents with incident response skills for dependency and supply chain compromise.
MCP server for Abnormal Security — AI-powered threat detection, case management, and email remediation
Deterministic registry + supply-chain integrity scanner for MCP (Model Context Protocol) servers. One-line install via npx, hash-pinned 112-entry DB, 4 advisory feeds, offline-first audit. Make MCP boring.
Lightweight MCP server demonstrating FF3 Format Preserving Encryption with multi-mode authentication. Shows how LLMs can securely encrypt/decrypt sensitive data while preserving format. Supports stdio and HTTP transports.
Simple Clickhouse interaction MCP server.
A 5-minute safety scanner for AI agent repos, MCP configs, local automation notes, and risky GitHub Actions permissions.
Free threat intelligence API for AI agents. CERT-In India advisories, UPI fraud detection, phishing/IP/CVE analysis. Part of Sentinel Series with SentinelCorp (company risk).
A collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools and more.
OAuth 2.1 authorization server for remote MCP servers. PKCE, refresh tokens, and CIMD support.
FastAPI → MCP bridge with built-in security audit + runtime prompt-injection guardrail. One line to expose to Claude/ChatGPT/Gemini, one line to verify it's safe, one line to block injection at runtime.
Independent AI/LLM security research — 10 shipped fixes, 5 GHSA advisories; focus on multi-tenant isolation, MCP protocol attack surface, SSRF/cookie boundary leakage